集智百科 - 复杂系统|人工智能|复杂科学|复杂网络|自组织 - 用户贡献 [zh-cn]

动态网络分析

2020-09-27T02:37:03Z

Zc1234567：

本词条由Ryan初步翻译

{{More citations needed|date=April 2009}}

'''Dynamic network analysis''' ('''DNA''') is an emergent scientific field that brings together traditional [[social network analysis]] (SNA), [[link analysis]] (LA), [[social simulation]] and [[multi-agent systems]] (MAS) within [[network science]] and [[network theory]]. There are two aspects of this field. The first is the [[statistical analysis]] of DNA data. The second is the utilization of simulation to address issues of network dynamics. DNA networks vary from traditional social networks in that they are larger, dynamic, multi-mode, multi-plex networks, and may contain varying levels of [[uncertainty]]. The main difference of DNA to SNA is that DNA takes interactions of social features conditioning structure and behavior of networks into account. DNA is tied to temporal analysis but temporal analysis is not necessarily tied to DNA, as changes in networks sometimes result from external factors which are independent of social features found in networks. One of the most notable and earliest of cases in the use of DNA is in Sampson's monastery study, where he took snapshots of the same network from different intervals and observed and analyzed the evolution of the network.<ref>Harrison C. White, 1992, Identity and control: A structural theory of social action. Princeton University Press.</ref> An early study of the dynamics of link utilization in very large-scale complex networks provides evidence of dynamic centrality, dynamic motifs, and cycles of social interactions.<ref>Dan Braha, Yaneer Bar‐Yam, 2006, [https://static1.squarespace.com/static/5b68a4e4a2772c2a206180a1/t/5c5de3faf4e1fc43e7b3d21e/1549657083988/Complexity_Braha_Original_w_Cover.pdf “From centrality to temporary fame: Dynamic centrality in complex networks,”] Complexity, 12(2), 59-63.</ref><ref>Dan Braha, Yaneer Bar-Yam 2009, [https://static1.squarespace.com/static/5b68a4e4a2772c2a206180a1/t/5c5de35feb393115883fdb54/1549656928806/DN_June_12_2008_necsi_Web.pdf Time-dependent complex networks: Dynamic centrality, dynamic motifs, and cycles of social interactions.] In Adaptive Networks (pp. 39-50). Springer, Berlin, Heidelberg.</ref>

Dynamic network analysis (DNA) is an emergent scientific field that brings together traditional social network analysis (SNA), link analysis (LA), social simulation and multi-agent systems (MAS) within network science and network theory. There are two aspects of this field. The first is the statistical analysis of DNA data. The second is the utilization of simulation to address issues of network dynamics. DNA networks vary from traditional social networks in that they are larger, dynamic, multi-mode, multi-plex networks, and may contain varying levels of uncertainty. The main difference of DNA to SNA is that DNA takes interactions of social features conditioning structure and behavior of networks into account. DNA is tied to temporal analysis but temporal analysis is not necessarily tied to DNA, as changes in networks sometimes result from external factors which are independent of social features found in networks. One of the most notable and earliest of cases in the use of DNA is in Sampson's monastery study, where he took snapshots of the same network from different intervals and observed and analyzed the evolution of the network. An early study of the dynamics of link utilization in very large-scale complex networks provides evidence of dynamic centrality, dynamic motifs, and cycles of social interactions.

'''动态网络分析 Dynamic network analysis'''是将传统的'''社会网络分析 Social Network Analysis SNA'''、'''链路分析 Link Analysis LA'''、'''社会模拟 Social Simulation'''和'''多主体系统 Multi-Agent Systems MAS'''与'''网络科学 Network Science'''和'''网络理论 Network Theory'''相结合的新兴科学领域。这个领域有两个方向。第一个是动态网络分析数据的统计分析。第二是利用仿真来解决网络动态问题。动态网络分析的网络不同于传统的社会网络，因为它们更加庞大、更加具有活力、多模式，多重网络，并且可能包含不同程度的不确定性。DNA 与 SNA 的主要区别在于，动态网络分析考虑了社会特征的交互作用，从而调节了网络的结构和行为。动态网络分析与'''时间分析 Temporal Analysis'''有关，但时间分析并不一定与动态网络分析有关，因为网络的变化有时是由外部因素造成的，这些因素与网络中的社会特征相互独立。关于使用动态网络分析中最早且最著名的案例之一，桑普森修道院的研究，他在该研究中从不同间隔拍摄了相同网络的快照，并观察和分析了网络的演变。对超大规模复杂网络中链接利用动态特性的早期研究提供了'''动态中心性 Dynamic Centrality'''，'''动态主题 Dynamic Motifs'''和'''社交互动周期 Cycles of Social Interactions'''的证据。

DNA statistical tools are generally optimized for large-scale networks and admit the analysis of multiple networks simultaneously in which, there are multiple types of [[Node (networking)|nodes]] (multi-node) and multiple types of links (multi-plex). Multi-node multi-plex networks are generally referred to as

DNA statistical tools are generally optimized for large-scale networks and admit the analysis of multiple networks simultaneously in which, there are multiple types of nodes (multi-node) and multiple types of links (multi-plex). Multi-node multi-plex networks are generally referred to as

DNA统计工具通常可针对大规模网络进行优化，同时允许对多个具有多种类型的节点(多节点)和多种类型的链接(多边)的网络进行分析。多节点多重网络通常被称为

meta-networks or high-dimensional networks. In contrast, SNA statistical tools focus on single or at most two mode data and facilitate the analysis of only one type of link at a time.

meta-networks or high-dimensional networks. In contrast, SNA statistical tools focus on single or at most two mode data and facilitate the analysis of only one type of link at a time.

'''元网络 Meta-Network'''或'''高维网络 High-Dimensional Networks'''。相比之下，SNA统计工具侧重于单一模式或至多两种模式的数据，一次只能进行一种类型链接的分析。

DNA statistical tools tend to provide more measures to the user, because they have measures that use data drawn from multiple networks simultaneously. Latent space models (Sarkar and Moore, 2005)<ref name="social"/> and agent-based simulation are often used to examine dynamic social networks (Carley et al., 2009).<ref name="Etiology"/> From a computer simulation perspective, nodes in DNA are like atoms in quantum theory, nodes can be, though need not be, treated as probabilistic. Whereas nodes in a traditional SNA model are [[wikt:static|static]], nodes in a DNA model have the ability to learn. Properties change over time; nodes can adapt: A company's employees can learn new skills and increase their value to the network; or, capture one terrorist and three more are forced to improvise. Change propagates from one node to the next and so on. DNA adds the element of a network's evolution and considers the circumstances under which change is likely to occur.

DNA statistical tools tend to provide more measures to the user, because they have measures that use data drawn from multiple networks simultaneously. Latent space models (Sarkar and Moore, 2005) and agent-based simulation are often used to examine dynamic social networks (Carley et al., 2009). From a computer simulation perspective, nodes in DNA are like atoms in quantum theory, nodes can be, though need not be, treated as probabilistic. Whereas nodes in a traditional SNA model are static, nodes in a DNA model have the ability to learn. Properties change over time; nodes can adapt: A company's employees can learn new skills and increase their value to the network; or, capture one terrorist and three more are forced to improvise. Change propagates from one node to the next and so on. DNA adds the element of a network's evolution and considers the circumstances under which change is likely to occur.

DNA统计工具倾向于为用户提供更多的测量手段，因为它们的测量手段同时从多个网络中提取的数据。'''潜在空间模型 Latent Space Models'''(Sarkar 和 Moore，2005年)和'''基于代理的模拟 Agent-Based Simulation'''经常用来测试动态的社交网络(Carley 等人，2009年)。从计算机仿真的角度来看，DNA中的节点就像量子理论中的原子一样，尽管不一定需要将节点视为概率随机的。传统SNA模型中的节点是静态的，而DNA模型中的节点具有学习能力。特性随时间变化; 节点可以随之适应: 一个公司的职员可以学习新技能，增加他们在公司结构中的价值; 或者，抓捕了一名恐怖分子，另外三人被迫临时合作。变化从一个节点传播到下一个节点，依此类推。DNA增加了网络进化的基本要素，并考虑了可能发生变化的环境。

[[Image:DynamicNetworkAnalysisExample.jpg|right|340px|thumb|
图1：An example of a multi-entity, multi-network, dynamic network diagram 多实体、多网络、动态网络图示]]

There are three main features to dynamic network analysis that distinguish it from standard social network analysis. First, rather than just using social networks, DNA looks at meta-networks. Second, agent-based modeling and other forms of simulations are often used to explore how networks evolve and adapt as well as the impact of interventions on those networks. Third, the links in the network are not binary; in fact, in many cases they represent the probability that there is a link.

There are three main features to dynamic network analysis that distinguish it from standard social network analysis. First, rather than just using social networks, DNA looks at meta-networks. Second, agent-based modeling and other forms of simulations are often used to explore how networks evolve and adapt as well as the impact of interventions on those networks. Third, the links in the network are not binary; in fact, in many cases they represent the probability that there is a link.

动态网络分析与标准社交网络分析相比，有三个主要特征。第一，DNA研究的不仅仅是社交网络，而是元网络。其次，基于代理建模和其他形式模拟常用于探索网络如何演变与适应，以及人为干预对这些网络的影响。第三，网络中的链接不是二进制的; 事实上，在许多情况中它们代表了链接存在的可能性。

==Meta-network 元网络==

A meta-network is a multi-mode, multi-link, multi-level network. Multi-mode means that there are many types of nodes; e.g., nodes people and locations. Multi-link means that there are many types of links; e.g., friendship and advice. Multi-level means that some nodes may be members of other nodes, such as a network composed of people and organizations and one of the links is who is a member of which organization.

A meta-network is a multi-mode, multi-link, multi-level network. Multi-mode means that there are many types of nodes; e.g., nodes people and locations. Multi-link means that there are many types of links; e.g., friendship and advice. Multi-level means that some nodes may be members of other nodes, such as a network composed of people and organizations and one of the links is who is a member of which organization.

'''元网络 Meta-Network'''是一种多模式、多链接、多层级的网络。多模式意味着有多种类型的节点; 例如，人与位置坐标的节点。多链接意味有着众多类型的链接，例如友谊和建议。多层级表明某些节点可能是其他节点的组成部分，例如由人员和组织构成的网络，并且链接之一就是谁是哪个组织的成员。

While different researchers use different modes, common modes reflect who, what, when, where, why and how. A simple example of a meta-network is the PCANS formulation with people, tasks, and resources.<ref name="pcans"/> A more detailed formulation considers people, tasks, resources, knowledge, and organizations.<ref name="smartAgents"/> The ORA tool was developed to support meta-network analysis.<ref name="toolkit" />

While different researchers use different modes, common modes reflect who, what, when, where, why and how. A simple example of a meta-network is the PCANS formulation with people, tasks, and resources. A more detailed formulation considers people, tasks, resources, knowledge, and organizations. The ORA tool was developed to support meta-network analysis.

虽然不同的研究人员使用不同的模式，共同的模式却都反映了何人、何事、时间、地点、原因和方式。一个简单的元网络示例是包含有人员、任务和资源的 PCANS 公式。更详细的公式会考虑人员、任务、资源、知识和组织。ORA工具是为支持元网络分析而开发。

==Illustrative problems that people in the DNA area work on DNA领域的工作者们正在研究的解释性问题==

--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“该段落中多次出现“...over time”，”是否该翻译为“在时间维度上”，留有迟疑。

* Developing metrics and statistics to assess and identify change within and across networks.
制定指标和统计资料，以评估和识别网络内部和网络之间的变化。

* Developing and validating simulations to study network change, evolution, adaptation, decay. See [[Computer simulation and organizational studies]]
开发和验证仿真以研究网络的变化，演变，适应性，衰减。

* Developing and testing theory of network change, evolution, adaptation, decay<ref>{{cite journal|author=Majdandzic, A.|title=Spontaneous recovery in dynamical networks|journal=Nature Physics|volume=10|pages=34–38|year=2013|doi=10.1038/nphys2819|display-authors=etal}}</ref>
网络变化，演化，适应，衰减的开发和测试理论

* Developing and validating formal models of network generation and evolution
开发和验证网络成长和演化的正规模型

* Developing techniques to visualize network change overall or at the node or group level
开发技术以将整体、节点或组级别的网络改变可视化

* Developing statistical techniques to see whether differences observed over time in networks are due to simply different samples from a distribution of links and nodes or changes over time in the underlying distribution of links and nodes
开发统计技术，以了解随着时间推移，在网络中观察到的差异是否仅仅是因为链接和节点分布的不同样本，还是因为链接和节点的基础分布随时间的变化

* Developing control processes for networks over time
在时间维度上，为网络开发控制过程

* Developing algorithms to change distributions of links in networks over time
在时间维度上，开发算法来改变网络中的链接分布

* Developing algorithms to track groups in networks over time
在时间维度上，开发算法来跟踪网络中的群体

* Developing tools to extract or locate networks from various data sources such as texts
开发从各种数据源资源(如文本)中提取或定位网络的工具

* Developing statistically valid measurements on networks over time
在时间维度上，在网络上开发有效的统计测量手段

* Examining the robustness of network metrics under various types of missing data
测试网络指标在不同类型数据缺失下的稳健性

* Empirical studies of multi-mode multi-link multi-time period networks
多模式、多链路、多时段网络的实证研究

* Examining networks as probabilistic time-variant phenomena
检验网络的概率时变现象

* Forecasting change in existing networks
预测现有网络的变化

* Identifying trails through time given a sequence of networks
在给定一系列网络的情况下识别经过时间的轨迹

* Identifying changes in node criticality given a sequence of networks anything else related to multi-mode multi-link multi-time period networks
在给定的网络序列中，识别节点临界性的变化与多模式、多链路、多时段网络相关的任何事物

* Studying random walks on temporal networks<ref name="rw" />
研究时态网络上的随机游动

* Quantifying structural properties of contact sequences in dynamic networks, which influence dynamical processes<ref name="betweenness"/>
动态网络中影响动态过程的接触序列结构特性的量化

*Assessment of covert activity<ref name="covert" /> and dark networks<ref name="dark" />
秘密活动的评估

*Citational analysis<ref name="citation" />
引文分析

*Social media analysis<ref name="socialmedia" />
社交媒体分析

*Assessment of public health systems<ref name="health" />
公共卫生系统的评估

*Analysis of hospital safety outcomes<ref name="hospital" />
医院安全结果分析

*Assessment of the structure of ethnic violence from news data<ref name="ethnic" />
新闻数据中种族暴力结构的评估

*Assessment of terror groups<ref name="terror" />
恐怖组织的评估

*Online social decay of social interactions<ref name="socialdecay" />
社交互动的在线社交衰退

*Visualization of large financial networks over time<ref name="dnb" />
在时间维度上，大型金融网络可视化

*Modelling of classroom interactions in schools<ref name="edu" />
学校课堂互动的建模

== See also ==

* [[Graph dynamical system]]
图动态系统

* [[International Network for Social Network Analysis]]
国际社交网络的分析

* [[Kathleen M. Carley]]
凯瑟琳·卡利

* [[Network dynamics]]
网络动力学

* [[Network science]]
网络科学

* [[Sequential dynamical system]]ios13.3 deca mield(8)
顺序动力学系统

==References==

{{Reflist|refs=

{{Reflist|refs=

{通货再膨胀 | 参考文献

<ref name="pcans">David Krackhardt and Kathleen M. Carley, 1998, "A PCANS Model of Structure in Organization," In proceedings of the 1998 International Symposium on Command and Control Research and Technology, Monterey, CA, June 1998, Evidence Based Research, Vienna, VA, Pp. 113-119.</ref>

<ref name="smartAgents">Kathleen M. Carley, 2002, "Smart Agents and Organizations of the Future," The Handbook of New Media. Edited by Leah Lievrouw and Sonia Livingstone (Eds.), Thousand Oaks, CA, Sage, Ch. 12: 206-220.</ref>

<ref name="rw">Michele Starnini, Andrea Baronchelli, Alain Barrat, 2012, Random walks on temporal networks. Phys. Rev. E 85, 056115, http://link.aps.org/doi/10.1103/PhysRevE.85.056115</ref>

<ref name="betweenness">René Pfitzner, Ingo Scholtes, Antonios Garas, Claudio Juan Tessone, Frank Schweitzer, 2012, "Betweenness Preference: Quantifying Correlations in the Topological Dynamics of Temporal Networks", Physical Review Letters, Vol. 110, May 10, 2013.</ref>

<ref name="social">Purnamrita Sarkar and Andrew W. Moore. 2005. Dynamic social network analysis using latent space models. SIGKDD Explor. Newsl. 7, 2 (December 2005), 31-40.</ref>

<ref name="covert">Carley, Kathleen M., Michael K., Martin and John P. Hancock, 2009, "Dynamic Network Analysis Applied to Experiments from the Decision Architectures Research Environment," Advanced Decision Architectures for the Warfigher: Foundation and Technology, Ch. 4.</ref>

<ref name="Etiology">Kathleen M. Carley, Michael K. Martin and Brian Hirshman, 2009, "The Etiology of Social Change," Topics in Cognitive Science, 1.4:621-650</ref>

<ref name="dark">Everton, Sean, 2012, Disrupting Dark Networks, Cambridge University Press, New York, NY</ref>

<ref name="citation">Kas, Miray, Kathleen M. Carley and L. Richard Carley, 2012, "Who was Where, When? Spatiotemporal Analysis of Researcher Mobility in Nuclear Science," In proceedings of the International Workshop on Spatio Temporal data Integration and Retrieval (STIR 2012), held in conjunction

<ref name="citation">Kas, Miray, Kathleen M. Carley and L. Richard Carley, 2012, "Who was Where, When? Spatiotemporal Analysis of Researcher Mobility in Nuclear Science," In proceedings of the International Workshop on Spatio Temporal data Integration and Retrieval (STIR 2012), held in conjunction

Miray，Kathleen m. Carley and l. Richard Carley，2012，“ Who was Where，When？核科学中研究人员流动性的时空分析” ，在国际时空数据整合与检索研讨会(STIR，2012)的会议记录中，同时举行

with ICDE 2012, April 1, 2012, Washington D.C.</ref>

with ICDE 2012, April 1, 2012, Washington D.C.</ref>

2012，April 1,2012，Washington d.c. / ref

<ref name="terror">Kenney, Michael J., John Horgan, Cale Horne, Peter Vining, Kathleen M. Carley, Michael Bigrigg, [[Mia Bloom]], Kurt Braddock, 2012, Organizational adaptation in an activist network: Social networks, leadership, and change in al-Muhajiroun, Applied Ergonomics, 44(5):739-747.</ref>

<ref name="health">Merrill, Jacqueline, Mark G. Orr, Christie Y. Jeon, Rosalind V. Wilson, Jonathan Storrick and Kathleen M. Carley, 2012, "Topology of Local Health Officials’ Advice Networks: Mind the Gaps," Journal of Public Health Management Practice, 18(6): 602–608</ref>

<ref name="ethnic">Van Holt, Tracy, Jeffrey C. Johnson, Jamie Brinkley, Kathleen M. Carley and Janna Caspersen, 2012, "Structure of ethnic violence in Sudan: an automated content, meta-network and geospatial analytical approach," Computational and Mathematical Organization Theory, 18:340-355.</ref>

<ref name="hospital">Effken, Judith A.,Sheila Gephart and Kathleen M. Carley, 2013, "Using ORA to Assess the Relationship of Handoffs to Quality and Safety Outcomes," Computers, Informatics, Nursing. 31(1): 36-44.</ref>

<ref name="socialmedia">Carley, Kathleen. M., Jürgen Pfeffer, [[Huan Liu]], Fred Morstatter, Rebecca Goolsby, 2013, Near Real Time Assessment of Social Media Using Geo-Temporal Network Analytics, In Proceedings of 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), August 25–28, 2013, Niagara Falls, Canada.</ref>

<ref name="toolkit">Kathleen M. Carley. 2014. "ORA: A Toolkit for Dynamic Network Analysis and Visualization," In Reda Alhajj and Jon Rokne (Eds.) Encyclopedia of Social Network Analysis and Mining, Springer.</ref>

<ref name="socialdecay">M. Abufouda, K. A. Zweig ."A Theoretical Model for Understanding the Dynamics of Online Social Networks Decay". arXiv preprint arXiv:1610.01538.</ref>

<ref name="dnb">{{cite journal|last1=Heijmans|first1=Ronald|last2=Heuver|first2=Richard|last3=Levallois|first3=Clement|last4=van Lelyveld|first4=Iman|title=Dynamic visualization of large financial networks|journal=The Journal of Network Theory in Finance|volume=2|issue=2|year=2016|pages=57–79|issn=2055-7795|doi=10.21314/JNTF.2016.017}}</ref>

<ref name="edu">Christian Bokhove, 2016, "Exploring classroom interaction with dynamic social network analysis", International Journal of Research & Method in Education, doi:10.1080/1743727X.2016.1192116.</ref>

}}

}}

}}

== Further reading ==

*Kathleen M. Carley, 2003, "Dynamic Network Analysis" in Dynamic Social Network Modeling and Analysis: Workshop Summary and Papers, Ronald Breiger, Kathleen Carley, and Philippa Pattison, (Eds.) Committee on Human Factors, National Research Council, National Research Council. Pp. 133–145, Washington, DC.

*Kathleen M. Carley, 2002, "Smart Agents and Organizations of the Future" The Handbook of New Media. Edited by Leah Lievrouw and Sonia Livingstone, Ch. 12, pp. 206–220, Thousand Oaks, CA, Sage.

*Kathleen M. Carley, Jana Diesner, Jeffrey Reminga, Maksim Tsvetovat, 2008, Toward an Interoperable Dynamic Network Analysis Toolkit, DSS Special Issue on Cyberinfrastructure for Homeland Security: Advances in Information Sharing, Data Mining, and Collaboration Systems. [http://www.sciencedirect.com/science/journal/01679236 Decision Support Systems] 43(4):1324-1347 ([http://www.sciencedirect.com/science?_ob=ArticleURL&_udi=B6V8S-4KGG5P7-1&_user=4422&_coverDate=08%2F31%2F2007&_rdoc=20&_fmt=high&_orig=browse&_srch=doc-info(%23toc%235878%232007%23999569995%23665759%23FLA%23display%23Volume)&_cdi=5878&_sort=d&_docanchor=&_ct=52&_acct=C000059600&_version=1&_urlVersion=0&_userid=4422&md5=9459e84d7a8863039c7abd5065266250 article 20]{{dead link|date=March 2019|bot=medic}}{{cbignore|bot=medic}})

* Dan Braha and Yaneer Bar-Yam, 2006, [https://static1.squarespace.com/static/5b68a4e4a2772c2a206180a1/t/5c5def5124a694e75e6109bc/1549659985911/Theory_Time_Dependent.pdf "Time-Dependent Complex Networks."]

*Terrill L. Frantz, Kathleen M. Carley. 2009, Toward A Confidence Estimate For The Most-Central-Actor Finding. Academy of Management Annual Conference, Chicago, IL, USA, 7–11 August. (Awarded the Sage Publications/RM Division Best Student Paper Award)

*Petter Holme, Jari Saramäki, 2011, "Temporal networks". https://arxiv.org/abs/1108.1780

*C. Aggarwal, K. Subbian, 2014, "Evolutionary Network Analysis: A Survey". ACM Computing Surveys, 47(1). ([http://charuaggarwal.net/CSUR-2013-0157.pdf pdf])

== External links ==

* [http://www.eecs.harvard.edu/%7Eparkes/RadcliffeSeminar.htm Radcliffe Exploratory Seminar on Dynamic Networks]

* [http://www.casos.cs.cmu.edu/ Center for Computational Analysis of Social and Organizational Systems (CASOS)]

{{Social networking}}

{{DEFAULTSORT:Dynamic Network Analysis}}

[[Category:Computer network analysis]]

Category:Computer network analysis

类别: 计算机网络分析

[[Category:Social statistics]]

Category:Social statistics

类别: 社会统计

[[Category:Methods in sociology]]

Category:Methods in sociology

范畴: 社会学方法

<noinclude>

This page was moved from [[wikipedia:en:Dynamic network analysis]]. Its edit history can be viewed at [[动态网络分析/edithistory]]</noinclude>

[[Category:待整理页面]]

动态网络分析

2020-09-27T02:34:03Z

Zc1234567：

本词条由Ryan初步翻译

{{More citations needed|date=April 2009}}

'''Dynamic network analysis''' ('''DNA''') is an emergent scientific field that brings together traditional [[social network analysis]] (SNA), [[link analysis]] (LA), [[social simulation]] and [[multi-agent systems]] (MAS) within [[network science]] and [[network theory]]. There are two aspects of this field. The first is the [[statistical analysis]] of DNA data. The second is the utilization of simulation to address issues of network dynamics. DNA networks vary from traditional social networks in that they are larger, dynamic, multi-mode, multi-plex networks, and may contain varying levels of [[uncertainty]]. The main difference of DNA to SNA is that DNA takes interactions of social features conditioning structure and behavior of networks into account. DNA is tied to temporal analysis but temporal analysis is not necessarily tied to DNA, as changes in networks sometimes result from external factors which are independent of social features found in networks. One of the most notable and earliest of cases in the use of DNA is in Sampson's monastery study, where he took snapshots of the same network from different intervals and observed and analyzed the evolution of the network.<ref>Harrison C. White, 1992, Identity and control: A structural theory of social action. Princeton University Press.</ref> An early study of the dynamics of link utilization in very large-scale complex networks provides evidence of dynamic centrality, dynamic motifs, and cycles of social interactions.<ref>Dan Braha, Yaneer Bar‐Yam, 2006, [https://static1.squarespace.com/static/5b68a4e4a2772c2a206180a1/t/5c5de3faf4e1fc43e7b3d21e/1549657083988/Complexity_Braha_Original_w_Cover.pdf “From centrality to temporary fame: Dynamic centrality in complex networks,”] Complexity, 12(2), 59-63.</ref><ref>Dan Braha, Yaneer Bar-Yam 2009, [https://static1.squarespace.com/static/5b68a4e4a2772c2a206180a1/t/5c5de35feb393115883fdb54/1549656928806/DN_June_12_2008_necsi_Web.pdf Time-dependent complex networks: Dynamic centrality, dynamic motifs, and cycles of social interactions.] In Adaptive Networks (pp. 39-50). Springer, Berlin, Heidelberg.</ref>

Dynamic network analysis (DNA) is an emergent scientific field that brings together traditional social network analysis (SNA), link analysis (LA), social simulation and multi-agent systems (MAS) within network science and network theory. There are two aspects of this field. The first is the statistical analysis of DNA data. The second is the utilization of simulation to address issues of network dynamics. DNA networks vary from traditional social networks in that they are larger, dynamic, multi-mode, multi-plex networks, and may contain varying levels of uncertainty. The main difference of DNA to SNA is that DNA takes interactions of social features conditioning structure and behavior of networks into account. DNA is tied to temporal analysis but temporal analysis is not necessarily tied to DNA, as changes in networks sometimes result from external factors which are independent of social features found in networks. One of the most notable and earliest of cases in the use of DNA is in Sampson's monastery study, where he took snapshots of the same network from different intervals and observed and analyzed the evolution of the network. An early study of the dynamics of link utilization in very large-scale complex networks provides evidence of dynamic centrality, dynamic motifs, and cycles of social interactions.

'''动态网络分析 Dynamic network analysis'''是将传统的'''社会网络分析 Social Network Analysis SNA'''、'''链路分析 Link Analysis LA'''、'''社会模拟 Social Simulation'''和'''多主体系统 Multi-Agent Systems MAS'''与'''网络科学 Network Science'''和'''网络理论 Network Theory'''相结合的新兴科学领域。这个领域有两个方向。第一个是动态网络分析数据的统计分析。第二是利用仿真来解决网络动态问题。动态网络分析的网络不同于传统的社会网络，因为它们更加庞大、更加具有活力、多模式，多重网络，并且可能包含不同程度的不确定性。DNA 与 SNA 的主要区别在于，动态网络分析考虑了社会特征的交互作用，从而调节了网络的结构和行为。动态网络分析与'''时间分析 Temporal Analysis'''有关，但时间分析并不一定与动态网络分析有关，因为网络的变化有时是由外部因素造成的，这些因素与网络中的社会特征相互独立。关于使用动态网络分析中最早且最著名的案例之一，桑普森修道院的研究，他在该研究中从不同间隔拍摄了相同网络的快照，并观察和分析了网络的演变。对超大规模复杂网络中链接利用动态特性的早期研究提供了'''动态中心性 Dynamic Centrality'''，'''动态主题 Dynamic Motifs'''和'''社交互动周期 Cycles of Social Interactions'''的证据。

DNA statistical tools are generally optimized for large-scale networks and admit the analysis of multiple networks simultaneously in which, there are multiple types of [[Node (networking)|nodes]] (multi-node) and multiple types of links (multi-plex). Multi-node multi-plex networks are generally referred to as

DNA statistical tools are generally optimized for large-scale networks and admit the analysis of multiple networks simultaneously in which, there are multiple types of nodes (multi-node) and multiple types of links (multi-plex). Multi-node multi-plex networks are generally referred to as

DNA统计工具通常可针对大规模网络进行优化，同时允许对多个具有多种类型的节点(多节点)和多种类型的链接(多边)的网络进行分析。多节点多重网络通常被称为

meta-networks or high-dimensional networks. In contrast, SNA statistical tools focus on single or at most two mode data and facilitate the analysis of only one type of link at a time.

meta-networks or high-dimensional networks. In contrast, SNA statistical tools focus on single or at most two mode data and facilitate the analysis of only one type of link at a time.

'''元网络 Meta-Network'''或'''高维网络 High-Dimensional Networks'''。相比之下，SNA统计工具侧重于单一模式或至多两种模式的数据，一次只能进行一种类型链接的分析。

DNA statistical tools tend to provide more measures to the user, because they have measures that use data drawn from multiple networks simultaneously. Latent space models (Sarkar and Moore, 2005)<ref name="social"/> and agent-based simulation are often used to examine dynamic social networks (Carley et al., 2009).<ref name="Etiology"/> From a computer simulation perspective, nodes in DNA are like atoms in quantum theory, nodes can be, though need not be, treated as probabilistic. Whereas nodes in a traditional SNA model are [[wikt:static|static]], nodes in a DNA model have the ability to learn. Properties change over time; nodes can adapt: A company's employees can learn new skills and increase their value to the network; or, capture one terrorist and three more are forced to improvise. Change propagates from one node to the next and so on. DNA adds the element of a network's evolution and considers the circumstances under which change is likely to occur.

DNA statistical tools tend to provide more measures to the user, because they have measures that use data drawn from multiple networks simultaneously. Latent space models (Sarkar and Moore, 2005) and agent-based simulation are often used to examine dynamic social networks (Carley et al., 2009). From a computer simulation perspective, nodes in DNA are like atoms in quantum theory, nodes can be, though need not be, treated as probabilistic. Whereas nodes in a traditional SNA model are static, nodes in a DNA model have the ability to learn. Properties change over time; nodes can adapt: A company's employees can learn new skills and increase their value to the network; or, capture one terrorist and three more are forced to improvise. Change propagates from one node to the next and so on. DNA adds the element of a network's evolution and considers the circumstances under which change is likely to occur.

DNA统计工具倾向于为用户提供更多的测量手段，因为它们的测量手段同时从多个网络中提取的数据。'''潜在空间模型 Latent Space Models'''(Sarkar 和 Moore，2005年)和'''基于代理的模拟 Agent-Based Simulation'''经常用来测试动态的社交网络(Carley 等人，2009年)。从计算机仿真的角度来看，DNA中的节点就像量子理论中的原子一样，尽管不一定需要将节点视为概率随机的。传统SNA模型中的节点是静态的，而DNA模型中的节点具有学习能力。特性随时间变化; 节点可以随之适应: 一个公司的职员可以学习新技能，增加他们在公司结构中的价值; 或者，抓捕了一名恐怖分子，另外三人被迫临时合作。变化从一个节点传播到下一个节点，依此类推。DNA增加了网络进化的基本要素，并考虑了可能发生变化的环境。

[[Image:DynamicNetworkAnalysisExample.jpg|right|340px|thumb|
图1：An example of a multi-entity, multi-network, dynamic network diagram 多实体、多网络、动态网络图示]]

There are three main features to dynamic network analysis that distinguish it from standard social network analysis. First, rather than just using social networks, DNA looks at meta-networks. Second, agent-based modeling and other forms of simulations are often used to explore how networks evolve and adapt as well as the impact of interventions on those networks. Third, the links in the network are not binary; in fact, in many cases they represent the probability that there is a link.

There are three main features to dynamic network analysis that distinguish it from standard social network analysis. First, rather than just using social networks, DNA looks at meta-networks. Second, agent-based modeling and other forms of simulations are often used to explore how networks evolve and adapt as well as the impact of interventions on those networks. Third, the links in the network are not binary; in fact, in many cases they represent the probability that there is a link.

动态网络分析与标准社交网络分析相比，有三个主要特征。第一，DNA研究的不仅仅是社交网络，而是元网络。其次，基于代理建模和其他形式模拟常用于探索网络如何演变与适应，以及人为干预对这些网络的影响。第三，网络中的链接不是二进制的; 事实上，在许多情况中它们代表了链接存在的可能性。

==Meta-network 元网络==

A meta-network is a multi-mode, multi-link, multi-level network. Multi-mode means that there are many types of nodes; e.g., nodes people and locations. Multi-link means that there are many types of links; e.g., friendship and advice. Multi-level means that some nodes may be members of other nodes, such as a network composed of people and organizations and one of the links is who is a member of which organization.

A meta-network is a multi-mode, multi-link, multi-level network. Multi-mode means that there are many types of nodes; e.g., nodes people and locations. Multi-link means that there are many types of links; e.g., friendship and advice. Multi-level means that some nodes may be members of other nodes, such as a network composed of people and organizations and one of the links is who is a member of which organization.

'''元网络 Meta-Network'''是一种多模式、多链接、多层级的网络。多模式意味着有多种类型的节点; 例如，人与位置坐标的节点。多链接意味有着众多类型的链接，例如友谊和建议。多层级表明某些节点可能是其他节点的组成部分，例如由人员和组织构成的网络，并且链接之一就是谁是哪个组织的成员。

While different researchers use different modes, common modes reflect who, what, when, where, why and how. A simple example of a meta-network is the PCANS formulation with people, tasks, and resources.<ref name="pcans"/> A more detailed formulation considers people, tasks, resources, knowledge, and organizations.<ref name="smartAgents"/> The ORA tool was developed to support meta-network analysis.<ref name="toolkit" />

While different researchers use different modes, common modes reflect who, what, when, where, why and how. A simple example of a meta-network is the PCANS formulation with people, tasks, and resources. A more detailed formulation considers people, tasks, resources, knowledge, and organizations. The ORA tool was developed to support meta-network analysis.

虽然不同的研究人员使用不同的模式，共同的模式却都反映了何人、何事、时间、地点、原因和方式。一个简单的元网络示例是包含有人员、任务和资源的 PCANS 公式。更详细的公式会考虑人员、任务、资源、知识和组织。ORA工具是为支持元网络分析而开发。

==Illustrative problems that people in the DNA area work on DNA领域的工作者们正在研究的解释性问题==

* Developing metrics and statistics to assess and identify change within and across networks.
制定指标和统计资料，以评估和识别网络内部和网络之间的变化。

* Developing and validating simulations to study network change, evolution, adaptation, decay. See [[Computer simulation and organizational studies]]
开发和验证仿真以研究网络的变化，演变，适应性，衰减。

* Developing and testing theory of network change, evolution, adaptation, decay<ref>{{cite journal|author=Majdandzic, A.|title=Spontaneous recovery in dynamical networks|journal=Nature Physics|volume=10|pages=34–38|year=2013|doi=10.1038/nphys2819|display-authors=etal}}</ref>
网络变化，演化，适应，衰减的开发和测试理论

* Developing and validating formal models of network generation and evolution
开发和验证网络成长和演化的正规模型

* Developing techniques to visualize network change overall or at the node or group level
开发技术以将整体、节点或组级别的网络改变可视化

* Developing statistical techniques to see whether differences observed over time in networks are due to simply different samples from a distribution of links and nodes or changes over time in the underlying distribution of links and nodes
开发统计技术，以了解随着时间推移，在网络中观察到的差异是否仅仅是因为链接和节点分布的不同样本，还是因为链接和节点的基础分布随时间的变化

* Developing control processes for networks over time
在时间维度上，为网络开发控制过程

* Developing algorithms to change distributions of links in networks over time
在时间维度上，开发算法来改变网络中的链接分布

* Developing algorithms to track groups in networks over time
在时间维度上，开发算法来跟踪网络中的群体

* Developing tools to extract or locate networks from various data sources such as texts
开发从各种数据源资源(如文本)中提取或定位网络的工具

* Developing statistically valid measurements on networks over time
在时间维度上，在网络上开发有效的统计测量手段

* Examining the robustness of network metrics under various types of missing data
测试网络指标在不同类型数据缺失下的稳健性

* Empirical studies of multi-mode multi-link multi-time period networks
多模式、多链路、多时段网络的实证研究

* Examining networks as probabilistic time-variant phenomena
检验网络的概率时变现象

* Forecasting change in existing networks
预测现有网络的变化

* Identifying trails through time given a sequence of networks
在给定一系列网络的情况下识别经过时间的轨迹

* Identifying changes in node criticality given a sequence of networks anything else related to multi-mode multi-link multi-time period networks
在给定的网络序列中，识别节点临界性的变化与多模式、多链路、多时段网络相关的任何事物

* Studying random walks on temporal networks<ref name="rw" />
研究时态网络上的随机游动

* Quantifying structural properties of contact sequences in dynamic networks, which influence dynamical processes<ref name="betweenness"/>
动态网络中影响动态过程的接触序列结构特性的量化

*Assessment of covert activity<ref name="covert" /> and dark networks<ref name="dark" />
秘密活动的评估

*Citational analysis<ref name="citation" />
引文分析

*Social media analysis<ref name="socialmedia" />
社交媒体分析

*Assessment of public health systems<ref name="health" />
公共卫生系统的评估

*Analysis of hospital safety outcomes<ref name="hospital" />
医院安全结果分析

*Assessment of the structure of ethnic violence from news data<ref name="ethnic" />
新闻数据中种族暴力结构的评估

*Assessment of terror groups<ref name="terror" />
恐怖组织的评估

*Online social decay of social interactions<ref name="socialdecay" />
社交互动的在线社交衰退

*Visualization of large financial networks over time<ref name="dnb" />
在时间维度上，大型金融网络可视化

*Modelling of classroom interactions in schools<ref name="edu" />
学校课堂互动的建模

== See also ==

* [[Graph dynamical system]]
图动态系统

* [[International Network for Social Network Analysis]]
国际社交网络的分析

* [[Kathleen M. Carley]]
凯瑟琳·卡利

* [[Network dynamics]]
网络动力学

* [[Network science]]
网络科学

* [[Sequential dynamical system]]ios13.3 deca mield(8)
顺序动力学系统

==References==

{{Reflist|refs=

{{Reflist|refs=

{通货再膨胀 | 参考文献

<ref name="pcans">David Krackhardt and Kathleen M. Carley, 1998, "A PCANS Model of Structure in Organization," In proceedings of the 1998 International Symposium on Command and Control Research and Technology, Monterey, CA, June 1998, Evidence Based Research, Vienna, VA, Pp. 113-119.</ref>

<ref name="smartAgents">Kathleen M. Carley, 2002, "Smart Agents and Organizations of the Future," The Handbook of New Media. Edited by Leah Lievrouw and Sonia Livingstone (Eds.), Thousand Oaks, CA, Sage, Ch. 12: 206-220.</ref>

<ref name="rw">Michele Starnini, Andrea Baronchelli, Alain Barrat, 2012, Random walks on temporal networks. Phys. Rev. E 85, 056115, http://link.aps.org/doi/10.1103/PhysRevE.85.056115</ref>

<ref name="betweenness">René Pfitzner, Ingo Scholtes, Antonios Garas, Claudio Juan Tessone, Frank Schweitzer, 2012, "Betweenness Preference: Quantifying Correlations in the Topological Dynamics of Temporal Networks", Physical Review Letters, Vol. 110, May 10, 2013.</ref>

<ref name="social">Purnamrita Sarkar and Andrew W. Moore. 2005. Dynamic social network analysis using latent space models. SIGKDD Explor. Newsl. 7, 2 (December 2005), 31-40.</ref>

<ref name="covert">Carley, Kathleen M., Michael K., Martin and John P. Hancock, 2009, "Dynamic Network Analysis Applied to Experiments from the Decision Architectures Research Environment," Advanced Decision Architectures for the Warfigher: Foundation and Technology, Ch. 4.</ref>

<ref name="Etiology">Kathleen M. Carley, Michael K. Martin and Brian Hirshman, 2009, "The Etiology of Social Change," Topics in Cognitive Science, 1.4:621-650</ref>

<ref name="dark">Everton, Sean, 2012, Disrupting Dark Networks, Cambridge University Press, New York, NY</ref>

<ref name="citation">Kas, Miray, Kathleen M. Carley and L. Richard Carley, 2012, "Who was Where, When? Spatiotemporal Analysis of Researcher Mobility in Nuclear Science," In proceedings of the International Workshop on Spatio Temporal data Integration and Retrieval (STIR 2012), held in conjunction

<ref name="citation">Kas, Miray, Kathleen M. Carley and L. Richard Carley, 2012, "Who was Where, When? Spatiotemporal Analysis of Researcher Mobility in Nuclear Science," In proceedings of the International Workshop on Spatio Temporal data Integration and Retrieval (STIR 2012), held in conjunction

Miray，Kathleen m. Carley and l. Richard Carley，2012，“ Who was Where，When？核科学中研究人员流动性的时空分析” ，在国际时空数据整合与检索研讨会(STIR，2012)的会议记录中，同时举行

with ICDE 2012, April 1, 2012, Washington D.C.</ref>

with ICDE 2012, April 1, 2012, Washington D.C.</ref>

2012，April 1,2012，Washington d.c. / ref

<ref name="terror">Kenney, Michael J., John Horgan, Cale Horne, Peter Vining, Kathleen M. Carley, Michael Bigrigg, [[Mia Bloom]], Kurt Braddock, 2012, Organizational adaptation in an activist network: Social networks, leadership, and change in al-Muhajiroun, Applied Ergonomics, 44(5):739-747.</ref>

<ref name="health">Merrill, Jacqueline, Mark G. Orr, Christie Y. Jeon, Rosalind V. Wilson, Jonathan Storrick and Kathleen M. Carley, 2012, "Topology of Local Health Officials’ Advice Networks: Mind the Gaps," Journal of Public Health Management Practice, 18(6): 602–608</ref>

<ref name="ethnic">Van Holt, Tracy, Jeffrey C. Johnson, Jamie Brinkley, Kathleen M. Carley and Janna Caspersen, 2012, "Structure of ethnic violence in Sudan: an automated content, meta-network and geospatial analytical approach," Computational and Mathematical Organization Theory, 18:340-355.</ref>

<ref name="hospital">Effken, Judith A.,Sheila Gephart and Kathleen M. Carley, 2013, "Using ORA to Assess the Relationship of Handoffs to Quality and Safety Outcomes," Computers, Informatics, Nursing. 31(1): 36-44.</ref>

<ref name="socialmedia">Carley, Kathleen. M., Jürgen Pfeffer, [[Huan Liu]], Fred Morstatter, Rebecca Goolsby, 2013, Near Real Time Assessment of Social Media Using Geo-Temporal Network Analytics, In Proceedings of 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), August 25–28, 2013, Niagara Falls, Canada.</ref>

<ref name="toolkit">Kathleen M. Carley. 2014. "ORA: A Toolkit for Dynamic Network Analysis and Visualization," In Reda Alhajj and Jon Rokne (Eds.) Encyclopedia of Social Network Analysis and Mining, Springer.</ref>

<ref name="socialdecay">M. Abufouda, K. A. Zweig ."A Theoretical Model for Understanding the Dynamics of Online Social Networks Decay". arXiv preprint arXiv:1610.01538.</ref>

<ref name="dnb">{{cite journal|last1=Heijmans|first1=Ronald|last2=Heuver|first2=Richard|last3=Levallois|first3=Clement|last4=van Lelyveld|first4=Iman|title=Dynamic visualization of large financial networks|journal=The Journal of Network Theory in Finance|volume=2|issue=2|year=2016|pages=57–79|issn=2055-7795|doi=10.21314/JNTF.2016.017}}</ref>

<ref name="edu">Christian Bokhove, 2016, "Exploring classroom interaction with dynamic social network analysis", International Journal of Research & Method in Education, doi:10.1080/1743727X.2016.1192116.</ref>

}}

}}

}}

== Further reading ==

*Kathleen M. Carley, 2003, "Dynamic Network Analysis" in Dynamic Social Network Modeling and Analysis: Workshop Summary and Papers, Ronald Breiger, Kathleen Carley, and Philippa Pattison, (Eds.) Committee on Human Factors, National Research Council, National Research Council. Pp. 133–145, Washington, DC.

*Kathleen M. Carley, 2002, "Smart Agents and Organizations of the Future" The Handbook of New Media. Edited by Leah Lievrouw and Sonia Livingstone, Ch. 12, pp. 206–220, Thousand Oaks, CA, Sage.

*Kathleen M. Carley, Jana Diesner, Jeffrey Reminga, Maksim Tsvetovat, 2008, Toward an Interoperable Dynamic Network Analysis Toolkit, DSS Special Issue on Cyberinfrastructure for Homeland Security: Advances in Information Sharing, Data Mining, and Collaboration Systems. [http://www.sciencedirect.com/science/journal/01679236 Decision Support Systems] 43(4):1324-1347 ([http://www.sciencedirect.com/science?_ob=ArticleURL&_udi=B6V8S-4KGG5P7-1&_user=4422&_coverDate=08%2F31%2F2007&_rdoc=20&_fmt=high&_orig=browse&_srch=doc-info(%23toc%235878%232007%23999569995%23665759%23FLA%23display%23Volume)&_cdi=5878&_sort=d&_docanchor=&_ct=52&_acct=C000059600&_version=1&_urlVersion=0&_userid=4422&md5=9459e84d7a8863039c7abd5065266250 article 20]{{dead link|date=March 2019|bot=medic}}{{cbignore|bot=medic}})

* Dan Braha and Yaneer Bar-Yam, 2006, [https://static1.squarespace.com/static/5b68a4e4a2772c2a206180a1/t/5c5def5124a694e75e6109bc/1549659985911/Theory_Time_Dependent.pdf "Time-Dependent Complex Networks."]

*Terrill L. Frantz, Kathleen M. Carley. 2009, Toward A Confidence Estimate For The Most-Central-Actor Finding. Academy of Management Annual Conference, Chicago, IL, USA, 7–11 August. (Awarded the Sage Publications/RM Division Best Student Paper Award)

*Petter Holme, Jari Saramäki, 2011, "Temporal networks". https://arxiv.org/abs/1108.1780

*C. Aggarwal, K. Subbian, 2014, "Evolutionary Network Analysis: A Survey". ACM Computing Surveys, 47(1). ([http://charuaggarwal.net/CSUR-2013-0157.pdf pdf])

== External links ==

* [http://www.eecs.harvard.edu/%7Eparkes/RadcliffeSeminar.htm Radcliffe Exploratory Seminar on Dynamic Networks]

* [http://www.casos.cs.cmu.edu/ Center for Computational Analysis of Social and Organizational Systems (CASOS)]

{{Social networking}}

{{DEFAULTSORT:Dynamic Network Analysis}}

[[Category:Computer network analysis]]

Category:Computer network analysis

类别: 计算机网络分析

[[Category:Social statistics]]

Category:Social statistics

类别: 社会统计

[[Category:Methods in sociology]]

Category:Methods in sociology

范畴: 社会学方法

<noinclude>

This page was moved from [[wikipedia:en:Dynamic network analysis]]. Its edit history can be viewed at [[动态网络分析/edithistory]]</noinclude>

[[Category:待整理页面]]

动态网络分析

2020-09-26T16:50:23Z

Zc1234567：

本词条由Ryan初步翻译

{{More citations needed|date=April 2009}}

'''Dynamic network analysis''' ('''DNA''') is an emergent scientific field that brings together traditional [[social network analysis]] (SNA), [[link analysis]] (LA), [[social simulation]] and [[multi-agent systems]] (MAS) within [[network science]] and [[network theory]]. There are two aspects of this field. The first is the [[statistical analysis]] of DNA data. The second is the utilization of simulation to address issues of network dynamics. DNA networks vary from traditional social networks in that they are larger, dynamic, multi-mode, multi-plex networks, and may contain varying levels of [[uncertainty]]. The main difference of DNA to SNA is that DNA takes interactions of social features conditioning structure and behavior of networks into account. DNA is tied to temporal analysis but temporal analysis is not necessarily tied to DNA, as changes in networks sometimes result from external factors which are independent of social features found in networks. One of the most notable and earliest of cases in the use of DNA is in Sampson's monastery study, where he took snapshots of the same network from different intervals and observed and analyzed the evolution of the network.<ref>Harrison C. White, 1992, Identity and control: A structural theory of social action. Princeton University Press.</ref> An early study of the dynamics of link utilization in very large-scale complex networks provides evidence of dynamic centrality, dynamic motifs, and cycles of social interactions.<ref>Dan Braha, Yaneer Bar‐Yam, 2006, [https://static1.squarespace.com/static/5b68a4e4a2772c2a206180a1/t/5c5de3faf4e1fc43e7b3d21e/1549657083988/Complexity_Braha_Original_w_Cover.pdf “From centrality to temporary fame: Dynamic centrality in complex networks,”] Complexity, 12(2), 59-63.</ref><ref>Dan Braha, Yaneer Bar-Yam 2009, [https://static1.squarespace.com/static/5b68a4e4a2772c2a206180a1/t/5c5de35feb393115883fdb54/1549656928806/DN_June_12_2008_necsi_Web.pdf Time-dependent complex networks: Dynamic centrality, dynamic motifs, and cycles of social interactions.] In Adaptive Networks (pp. 39-50). Springer, Berlin, Heidelberg.</ref>

Dynamic network analysis (DNA) is an emergent scientific field that brings together traditional social network analysis (SNA), link analysis (LA), social simulation and multi-agent systems (MAS) within network science and network theory. There are two aspects of this field. The first is the statistical analysis of DNA data. The second is the utilization of simulation to address issues of network dynamics. DNA networks vary from traditional social networks in that they are larger, dynamic, multi-mode, multi-plex networks, and may contain varying levels of uncertainty. The main difference of DNA to SNA is that DNA takes interactions of social features conditioning structure and behavior of networks into account. DNA is tied to temporal analysis but temporal analysis is not necessarily tied to DNA, as changes in networks sometimes result from external factors which are independent of social features found in networks. One of the most notable and earliest of cases in the use of DNA is in Sampson's monastery study, where he took snapshots of the same network from different intervals and observed and analyzed the evolution of the network. An early study of the dynamics of link utilization in very large-scale complex networks provides evidence of dynamic centrality, dynamic motifs, and cycles of social interactions.

'''动态网络分析 Dynamic network analysis'''是将传统的'''社会网络分析 Social Network Analysis SNA'''、'''链路分析 Link Analysis LA'''、'''社会模拟 Social Simulation'''和'''多主体系统 Multi-Agent Systems MAS'''与'''网络科学 Network Science'''和'''网络理论 Network Theory'''相结合的新兴科学领域。这个领域有两个方向。第一个是动态网络分析数据的统计分析。第二是利用仿真来解决网络动态问题。动态网络分析的网络不同于传统的社会网络，因为它们更加庞大、更加具有活力、多模式，多重网络，并且可能包含不同程度的不确定性。DNA 与 SNA 的主要区别在于，动态网络分析考虑了社会特征的交互作用，从而调节了网络的结构和行为。动态网络分析与'''时间分析 Temporal Analysis'''有关，但时间分析并不一定与动态网络分析有关，因为网络的变化有时是由外部因素造成的，这些因素与网络中的社会特征相互独立。关于使用动态网络分析中最早且最著名的案例之一，桑普森修道院的研究，他在该研究中从不同间隔拍摄了相同网络的快照，并观察和分析了网络的演变。对超大规模复杂网络中链接利用动态特性的早期研究提供了'''动态中心性 Dynamic Centrality'''，'''动态主题 Dynamic Motifs'''和'''社交互动周期 Cycles of Social Interactions'''的证据。

DNA statistical tools are generally optimized for large-scale networks and admit the analysis of multiple networks simultaneously in which, there are multiple types of [[Node (networking)|nodes]] (multi-node) and multiple types of links (multi-plex). Multi-node multi-plex networks are generally referred to as

DNA statistical tools are generally optimized for large-scale networks and admit the analysis of multiple networks simultaneously in which, there are multiple types of nodes (multi-node) and multiple types of links (multi-plex). Multi-node multi-plex networks are generally referred to as

DNA统计工具通常可针对大规模网络进行优化，同时允许对多个具有多种类型的节点(多节点)和多种类型的链接(多边)的网络进行分析。多节点多重网络通常被称为

meta-networks or high-dimensional networks. In contrast, SNA statistical tools focus on single or at most two mode data and facilitate the analysis of only one type of link at a time.

meta-networks or high-dimensional networks. In contrast, SNA statistical tools focus on single or at most two mode data and facilitate the analysis of only one type of link at a time.

'''元网络 Meta-Network'''或'''高维网络 High-Dimensional Networks'''。相比之下，SNA统计工具侧重于单一模式或至多两种模式的数据，一次只能进行一种类型链接的分析。

DNA statistical tools tend to provide more measures to the user, because they have measures that use data drawn from multiple networks simultaneously. Latent space models (Sarkar and Moore, 2005)<ref name="social"/> and agent-based simulation are often used to examine dynamic social networks (Carley et al., 2009).<ref name="Etiology"/> From a computer simulation perspective, nodes in DNA are like atoms in quantum theory, nodes can be, though need not be, treated as probabilistic. Whereas nodes in a traditional SNA model are [[wikt:static|static]], nodes in a DNA model have the ability to learn. Properties change over time; nodes can adapt: A company's employees can learn new skills and increase their value to the network; or, capture one terrorist and three more are forced to improvise. Change propagates from one node to the next and so on. DNA adds the element of a network's evolution and considers the circumstances under which change is likely to occur.

DNA statistical tools tend to provide more measures to the user, because they have measures that use data drawn from multiple networks simultaneously. Latent space models (Sarkar and Moore, 2005) and agent-based simulation are often used to examine dynamic social networks (Carley et al., 2009). From a computer simulation perspective, nodes in DNA are like atoms in quantum theory, nodes can be, though need not be, treated as probabilistic. Whereas nodes in a traditional SNA model are static, nodes in a DNA model have the ability to learn. Properties change over time; nodes can adapt: A company's employees can learn new skills and increase their value to the network; or, capture one terrorist and three more are forced to improvise. Change propagates from one node to the next and so on. DNA adds the element of a network's evolution and considers the circumstances under which change is likely to occur.

DNA统计工具倾向于为用户提供更多的测量手段，因为它们的测量手段同时从多个网络中提取的数据。'''潜在空间模型 Latent Space Models'''(Sarkar 和 Moore，2005年)和'''基于代理的模拟 Agent-Based Simulation'''经常用来测试动态的社交网络(Carley 等人，2009年)。从计算机仿真的角度来看，DNA中的节点就像量子理论中的原子一样，尽管不一定需要将节点视为概率随机的。传统SNA模型中的节点是静态的，而DNA模型中的节点具有学习能力。特性随时间变化; 节点可以随之适应: 一个公司的职员可以学习新技能，增加他们在公司结构中的价值; 或者，抓捕了一名恐怖分子，另外三人被迫临时合作。变化从一个节点传播到下一个节点，依此类推。DNA增加了网络进化的基本要素，并考虑了可能发生变化的环境。

[[Image:DynamicNetworkAnalysisExample.jpg|right|340px|thumb|
图1：An example of a multi-entity, multi-network, dynamic network diagram 多实体、多网络、动态网络图示]]

There are three main features to dynamic network analysis that distinguish it from standard social network analysis. First, rather than just using social networks, DNA looks at meta-networks. Second, agent-based modeling and other forms of simulations are often used to explore how networks evolve and adapt as well as the impact of interventions on those networks. Third, the links in the network are not binary; in fact, in many cases they represent the probability that there is a link.

There are three main features to dynamic network analysis that distinguish it from standard social network analysis. First, rather than just using social networks, DNA looks at meta-networks. Second, agent-based modeling and other forms of simulations are often used to explore how networks evolve and adapt as well as the impact of interventions on those networks. Third, the links in the network are not binary; in fact, in many cases they represent the probability that there is a link.

动态网络分析与标准社交网络分析相比，有三个主要特征。第一，DNA研究的不仅仅是社交网络，而是元网络。其次，基于代理建模和其他形式模拟常用于探索网络如何演变与适应，以及人为干预对这些网络的影响。第三，网络中的链接不是二进制的; 事实上，在许多情况中它们代表了链接存在的可能性。

==Meta-network 元网络==

A meta-network is a multi-mode, multi-link, multi-level network. Multi-mode means that there are many types of nodes; e.g., nodes people and locations. Multi-link means that there are many types of links; e.g., friendship and advice. Multi-level means that some nodes may be members of other nodes, such as a network composed of people and organizations and one of the links is who is a member of which organization.

A meta-network is a multi-mode, multi-link, multi-level network. Multi-mode means that there are many types of nodes; e.g., nodes people and locations. Multi-link means that there are many types of links; e.g., friendship and advice. Multi-level means that some nodes may be members of other nodes, such as a network composed of people and organizations and one of the links is who is a member of which organization.

'''元网络 Meta-Network'''是一个多模式、多链路、多层次的网络。多模式意味着有许多类型的节点; 例如，人和位置。多链接意味着有许多类型的链接，例如，友谊和建议。多层级意味着某些节点可能是其他节点的成员，例如由人员和组织组成的网络，而链接之一就是谁是哪个组织的成员。

While different researchers use different modes, common modes reflect who, what, when, where, why and how. A simple example of a meta-network is the PCANS formulation with people, tasks, and resources.<ref name="pcans"/> A more detailed formulation considers people, tasks, resources, knowledge, and organizations.<ref name="smartAgents"/> The ORA tool was developed to support meta-network analysis.<ref name="toolkit" />

While different researchers use different modes, common modes reflect who, what, when, where, why and how. A simple example of a meta-network is the PCANS formulation with people, tasks, and resources. A more detailed formulation considers people, tasks, resources, knowledge, and organizations. The ORA tool was developed to support meta-network analysis.

虽然不同的研究人员使用不同的模式，共同的模式却都反映了谁，什么，什么时候，在哪里，为什么和如何。元网络的一个简单示例是包含人、任务和资源的 PCANS 公式。更详细的公式考虑人员、任务、资源、知识和组织。ORA工具是为支持元网络分析而开发的。

==Illustrative problems that people in the DNA area work on DNA领域的人们正在研究的说明性问题==

* Developing metrics and statistics to assess and identify change within and across networks.
开发度量和统计数据，以评估和识别网络内部和网络之间的变化。

* Developing and validating simulations to study network change, evolution, adaptation, decay. See [[Computer simulation and organizational studies]]
开发和验证仿真以研究网络的变化，演变，适应性，衰减。

* Developing and testing theory of network change, evolution, adaptation, decay<ref>{{cite journal|author=Majdandzic, A.|title=Spontaneous recovery in dynamical networks|journal=Nature Physics|volume=10|pages=34–38|year=2013|doi=10.1038/nphys2819|display-authors=etal}}</ref>
网络变化，演化，适应，衰减的开发和测试理论

* Developing and validating formal models of network generation and evolution
开发和验证网络生成和演化的正式模型

* Developing techniques to visualize network change overall or at the node or group level
开发技术以可视化整体或节点或组级别的网络变化

* Developing statistical techniques to see whether differences observed over time in networks are due to simply different samples from a distribution of links and nodes or changes over time in the underlying distribution of links and nodes
开发统计技术，以了解随着时间的推移，在网络中观察到的差异是否仅仅是因为链接和节点分布的样本不同，还是因为链接和节点的底层分布随时间的变化

* Developing control processes for networks over time
在时间维度上，为网络开发控制过程

* Developing algorithms to change distributions of links in networks over time
在时间维度上，开发算法来改变网络中的链接分布

* Developing algorithms to track groups in networks over time
在时间维度上，开发算法来跟踪网络中的群体

* Developing tools to extract or locate networks from various data sources such as texts
开发从各种数据源(如文本)中提取或定位网络的工具

* Developing statistically valid measurements on networks over time
在时间维度上，在网络上开发有效的统计度量

* Examining the robustness of network metrics under various types of missing data
检查网络指标在不同类型缺失数据下的鲁棒性

* Empirical studies of multi-mode multi-link multi-time period networks
多模式、多链路、多时段网络的实证研究

* Examining networks as probabilistic time-variant phenomena
检验网络的概率时变现象

* Forecasting change in existing networks
预测现有网络的变化

* Identifying trails through time given a sequence of networks
在给定网络序列的时间内识别路径

* Identifying changes in node criticality given a sequence of networks anything else related to multi-mode multi-link multi-time period networks
在给定的网络序列中识别节点临界性的变化，任何与多模式、多链路、多时段网络相关的东西

* Studying random walks on temporal networks<ref name="rw" />
研究时间网络上的随机游动

* Quantifying structural properties of contact sequences in dynamic networks, which influence dynamical processes<ref name="betweenness"/>
动态网络中影响动态过程的接触序列结构特性的量化

*Assessment of covert activity<ref name="covert" /> and dark networks<ref name="dark" />
秘密活动的评估

*Citational analysis<ref name="citation" />
引文分析

*Social media analysis<ref name="socialmedia" />
社交媒体分析

*Assessment of public health systems<ref name="health" />
公共卫生系统的评估

*Analysis of hospital safety outcomes<ref name="hospital" />
医院安全结果分析

*Assessment of the structure of ethnic violence from news data<ref name="ethnic" />
从新闻数据中评估种族暴力的结构

*Assessment of terror groups<ref name="terror" />
对恐怖组织的评估

*Online social decay of social interactions<ref name="socialdecay" />
社交互动的在线社交衰退

*Visualization of large financial networks over time<ref name="dnb" />
大型金融网络随时间的可视化

*Modelling of classroom interactions in schools<ref name="edu" />
学校课堂互动的建模

== See also ==

* [[Graph dynamical system]]
图动态系统

* [[International Network for Social Network Analysis]]
国际社交网络的分析

* [[Kathleen M. Carley]]
凯瑟琳·卡利

* [[Network dynamics]]
网络动力学

* [[Network science]]
网络科学

* [[Sequential dynamical system]]ios13.3 deca mield(8)
顺序动力学系统

==References==

{{Reflist|refs=

{{Reflist|refs=

{通货再膨胀 | 参考文献

<ref name="pcans">David Krackhardt and Kathleen M. Carley, 1998, "A PCANS Model of Structure in Organization," In proceedings of the 1998 International Symposium on Command and Control Research and Technology, Monterey, CA, June 1998, Evidence Based Research, Vienna, VA, Pp. 113-119.</ref>

<ref name="smartAgents">Kathleen M. Carley, 2002, "Smart Agents and Organizations of the Future," The Handbook of New Media. Edited by Leah Lievrouw and Sonia Livingstone (Eds.), Thousand Oaks, CA, Sage, Ch. 12: 206-220.</ref>

<ref name="rw">Michele Starnini, Andrea Baronchelli, Alain Barrat, 2012, Random walks on temporal networks. Phys. Rev. E 85, 056115, http://link.aps.org/doi/10.1103/PhysRevE.85.056115</ref>

<ref name="betweenness">René Pfitzner, Ingo Scholtes, Antonios Garas, Claudio Juan Tessone, Frank Schweitzer, 2012, "Betweenness Preference: Quantifying Correlations in the Topological Dynamics of Temporal Networks", Physical Review Letters, Vol. 110, May 10, 2013.</ref>

<ref name="social">Purnamrita Sarkar and Andrew W. Moore. 2005. Dynamic social network analysis using latent space models. SIGKDD Explor. Newsl. 7, 2 (December 2005), 31-40.</ref>

<ref name="covert">Carley, Kathleen M., Michael K., Martin and John P. Hancock, 2009, "Dynamic Network Analysis Applied to Experiments from the Decision Architectures Research Environment," Advanced Decision Architectures for the Warfigher: Foundation and Technology, Ch. 4.</ref>

<ref name="Etiology">Kathleen M. Carley, Michael K. Martin and Brian Hirshman, 2009, "The Etiology of Social Change," Topics in Cognitive Science, 1.4:621-650</ref>

<ref name="dark">Everton, Sean, 2012, Disrupting Dark Networks, Cambridge University Press, New York, NY</ref>

<ref name="citation">Kas, Miray, Kathleen M. Carley and L. Richard Carley, 2012, "Who was Where, When? Spatiotemporal Analysis of Researcher Mobility in Nuclear Science," In proceedings of the International Workshop on Spatio Temporal data Integration and Retrieval (STIR 2012), held in conjunction

<ref name="citation">Kas, Miray, Kathleen M. Carley and L. Richard Carley, 2012, "Who was Where, When? Spatiotemporal Analysis of Researcher Mobility in Nuclear Science," In proceedings of the International Workshop on Spatio Temporal data Integration and Retrieval (STIR 2012), held in conjunction

Miray，Kathleen m. Carley and l. Richard Carley，2012，“ Who was Where，When？核科学中研究人员流动性的时空分析” ，在国际时空数据整合与检索研讨会(STIR，2012)的会议记录中，同时举行

with ICDE 2012, April 1, 2012, Washington D.C.</ref>

with ICDE 2012, April 1, 2012, Washington D.C.</ref>

2012，April 1,2012，Washington d.c. / ref

<ref name="terror">Kenney, Michael J., John Horgan, Cale Horne, Peter Vining, Kathleen M. Carley, Michael Bigrigg, [[Mia Bloom]], Kurt Braddock, 2012, Organizational adaptation in an activist network: Social networks, leadership, and change in al-Muhajiroun, Applied Ergonomics, 44(5):739-747.</ref>

<ref name="health">Merrill, Jacqueline, Mark G. Orr, Christie Y. Jeon, Rosalind V. Wilson, Jonathan Storrick and Kathleen M. Carley, 2012, "Topology of Local Health Officials’ Advice Networks: Mind the Gaps," Journal of Public Health Management Practice, 18(6): 602–608</ref>

<ref name="ethnic">Van Holt, Tracy, Jeffrey C. Johnson, Jamie Brinkley, Kathleen M. Carley and Janna Caspersen, 2012, "Structure of ethnic violence in Sudan: an automated content, meta-network and geospatial analytical approach," Computational and Mathematical Organization Theory, 18:340-355.</ref>

<ref name="hospital">Effken, Judith A.,Sheila Gephart and Kathleen M. Carley, 2013, "Using ORA to Assess the Relationship of Handoffs to Quality and Safety Outcomes," Computers, Informatics, Nursing. 31(1): 36-44.</ref>

<ref name="socialmedia">Carley, Kathleen. M., Jürgen Pfeffer, [[Huan Liu]], Fred Morstatter, Rebecca Goolsby, 2013, Near Real Time Assessment of Social Media Using Geo-Temporal Network Analytics, In Proceedings of 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), August 25–28, 2013, Niagara Falls, Canada.</ref>

<ref name="toolkit">Kathleen M. Carley. 2014. "ORA: A Toolkit for Dynamic Network Analysis and Visualization," In Reda Alhajj and Jon Rokne (Eds.) Encyclopedia of Social Network Analysis and Mining, Springer.</ref>

<ref name="socialdecay">M. Abufouda, K. A. Zweig ."A Theoretical Model for Understanding the Dynamics of Online Social Networks Decay". arXiv preprint arXiv:1610.01538.</ref>

<ref name="dnb">{{cite journal|last1=Heijmans|first1=Ronald|last2=Heuver|first2=Richard|last3=Levallois|first3=Clement|last4=van Lelyveld|first4=Iman|title=Dynamic visualization of large financial networks|journal=The Journal of Network Theory in Finance|volume=2|issue=2|year=2016|pages=57–79|issn=2055-7795|doi=10.21314/JNTF.2016.017}}</ref>

<ref name="edu">Christian Bokhove, 2016, "Exploring classroom interaction with dynamic social network analysis", International Journal of Research & Method in Education, doi:10.1080/1743727X.2016.1192116.</ref>

}}

}}

}}

== Further reading ==

*Kathleen M. Carley, 2003, "Dynamic Network Analysis" in Dynamic Social Network Modeling and Analysis: Workshop Summary and Papers, Ronald Breiger, Kathleen Carley, and Philippa Pattison, (Eds.) Committee on Human Factors, National Research Council, National Research Council. Pp. 133–145, Washington, DC.

*Kathleen M. Carley, 2002, "Smart Agents and Organizations of the Future" The Handbook of New Media. Edited by Leah Lievrouw and Sonia Livingstone, Ch. 12, pp. 206–220, Thousand Oaks, CA, Sage.

*Kathleen M. Carley, Jana Diesner, Jeffrey Reminga, Maksim Tsvetovat, 2008, Toward an Interoperable Dynamic Network Analysis Toolkit, DSS Special Issue on Cyberinfrastructure for Homeland Security: Advances in Information Sharing, Data Mining, and Collaboration Systems. [http://www.sciencedirect.com/science/journal/01679236 Decision Support Systems] 43(4):1324-1347 ([http://www.sciencedirect.com/science?_ob=ArticleURL&_udi=B6V8S-4KGG5P7-1&_user=4422&_coverDate=08%2F31%2F2007&_rdoc=20&_fmt=high&_orig=browse&_srch=doc-info(%23toc%235878%232007%23999569995%23665759%23FLA%23display%23Volume)&_cdi=5878&_sort=d&_docanchor=&_ct=52&_acct=C000059600&_version=1&_urlVersion=0&_userid=4422&md5=9459e84d7a8863039c7abd5065266250 article 20]{{dead link|date=March 2019|bot=medic}}{{cbignore|bot=medic}})

* Dan Braha and Yaneer Bar-Yam, 2006, [https://static1.squarespace.com/static/5b68a4e4a2772c2a206180a1/t/5c5def5124a694e75e6109bc/1549659985911/Theory_Time_Dependent.pdf "Time-Dependent Complex Networks."]

*Terrill L. Frantz, Kathleen M. Carley. 2009, Toward A Confidence Estimate For The Most-Central-Actor Finding. Academy of Management Annual Conference, Chicago, IL, USA, 7–11 August. (Awarded the Sage Publications/RM Division Best Student Paper Award)

*Petter Holme, Jari Saramäki, 2011, "Temporal networks". https://arxiv.org/abs/1108.1780

*C. Aggarwal, K. Subbian, 2014, "Evolutionary Network Analysis: A Survey". ACM Computing Surveys, 47(1). ([http://charuaggarwal.net/CSUR-2013-0157.pdf pdf])

== External links ==

* [http://www.eecs.harvard.edu/%7Eparkes/RadcliffeSeminar.htm Radcliffe Exploratory Seminar on Dynamic Networks]

* [http://www.casos.cs.cmu.edu/ Center for Computational Analysis of Social and Organizational Systems (CASOS)]

{{Social networking}}

{{DEFAULTSORT:Dynamic Network Analysis}}

[[Category:Computer network analysis]]

Category:Computer network analysis

类别: 计算机网络分析

[[Category:Social statistics]]

Category:Social statistics

类别: 社会统计

[[Category:Methods in sociology]]

Category:Methods in sociology

范畴: 社会学方法

<noinclude>

This page was moved from [[wikipedia:en:Dynamic network analysis]]. Its edit history can be viewed at [[动态网络分析/edithistory]]</noinclude>

[[Category:待整理页面]]

动态网络分析

2020-09-25T16:42:14Z

Zc1234567：

本词条由Ryan初步翻译

{{More citations needed|date=April 2009}}

'''Dynamic network analysis''' ('''DNA''') is an emergent scientific field that brings together traditional [[social network analysis]] (SNA), [[link analysis]] (LA), [[social simulation]] and [[multi-agent systems]] (MAS) within [[network science]] and [[network theory]]. There are two aspects of this field. The first is the [[statistical analysis]] of DNA data. The second is the utilization of simulation to address issues of network dynamics. DNA networks vary from traditional social networks in that they are larger, dynamic, multi-mode, multi-plex networks, and may contain varying levels of [[uncertainty]]. The main difference of DNA to SNA is that DNA takes interactions of social features conditioning structure and behavior of networks into account. DNA is tied to temporal analysis but temporal analysis is not necessarily tied to DNA, as changes in networks sometimes result from external factors which are independent of social features found in networks. One of the most notable and earliest of cases in the use of DNA is in Sampson's monastery study, where he took snapshots of the same network from different intervals and observed and analyzed the evolution of the network.<ref>Harrison C. White, 1992, Identity and control: A structural theory of social action. Princeton University Press.</ref> An early study of the dynamics of link utilization in very large-scale complex networks provides evidence of dynamic centrality, dynamic motifs, and cycles of social interactions.<ref>Dan Braha, Yaneer Bar‐Yam, 2006, [https://static1.squarespace.com/static/5b68a4e4a2772c2a206180a1/t/5c5de3faf4e1fc43e7b3d21e/1549657083988/Complexity_Braha_Original_w_Cover.pdf “From centrality to temporary fame: Dynamic centrality in complex networks,”] Complexity, 12(2), 59-63.</ref><ref>Dan Braha, Yaneer Bar-Yam 2009, [https://static1.squarespace.com/static/5b68a4e4a2772c2a206180a1/t/5c5de35feb393115883fdb54/1549656928806/DN_June_12_2008_necsi_Web.pdf Time-dependent complex networks: Dynamic centrality, dynamic motifs, and cycles of social interactions.] In Adaptive Networks (pp. 39-50). Springer, Berlin, Heidelberg.</ref>

Dynamic network analysis (DNA) is an emergent scientific field that brings together traditional social network analysis (SNA), link analysis (LA), social simulation and multi-agent systems (MAS) within network science and network theory. There are two aspects of this field. The first is the statistical analysis of DNA data. The second is the utilization of simulation to address issues of network dynamics. DNA networks vary from traditional social networks in that they are larger, dynamic, multi-mode, multi-plex networks, and may contain varying levels of uncertainty. The main difference of DNA to SNA is that DNA takes interactions of social features conditioning structure and behavior of networks into account. DNA is tied to temporal analysis but temporal analysis is not necessarily tied to DNA, as changes in networks sometimes result from external factors which are independent of social features found in networks. One of the most notable and earliest of cases in the use of DNA is in Sampson's monastery study, where he took snapshots of the same network from different intervals and observed and analyzed the evolution of the network. An early study of the dynamics of link utilization in very large-scale complex networks provides evidence of dynamic centrality, dynamic motifs, and cycles of social interactions.

'''动态网络分析 Dynamic network analysis'''是将传统的'''社会网络分析 Social Network Analysis SNA'''、'''链路分析 Link Analysis LA'''、'''社会模拟 Social Simulation'''和'''多主体系统 Multi-Agent Systems MAS'''与'''网络科学 Network Science'''和'''网络理论 Network Theory'''相结合的新兴科学领域。这个领域有两个方向。第一个是动态网络分析数据的统计分析。第二是利用仿真来解决网络动态问题。动态网络分析的网络不同于传统的社会网络，因为它们更加庞大、更加具有活力、多模式，多重网络，并且可能包含不同程度的不确定性。DNA 与 SNA 的主要区别在于，动态网络分析考虑了社会特征的交互作用，从而调节了网络的结构和行为。动态网络分析与'''时间分析 Temporal Analysis'''有关，但时间分析并不一定与动态网络分析有关，因为网络的变化有时是由外部因素造成的，这些因素与网络中的社会特征相互独立。关于使用动态网络分析中最早且最著名的案例之一，桑普森修道院的研究，他在该研究中从不同间隔拍摄了相同网络的快照，并观察和分析了网络的演变。对超大规模复杂网络中链接利用动态特性的早期研究提供了'''动态中心性 Dynamic Centrality'''，'''动态主题 Dynamic Motifs'''和'''社交互动周期 Cycles of Social Interactions'''的证据。

DNA statistical tools are generally optimized for large-scale networks and admit the analysis of multiple networks simultaneously in which, there are multiple types of [[Node (networking)|nodes]] (multi-node) and multiple types of links (multi-plex). Multi-node multi-plex networks are generally referred to as

DNA statistical tools are generally optimized for large-scale networks and admit the analysis of multiple networks simultaneously in which, there are multiple types of nodes (multi-node) and multiple types of links (multi-plex). Multi-node multi-plex networks are generally referred to as

DNA统计工具通常可针对大规模网络进行优化，同时允许对多个具有多种类型的节点(多节点)和多种类型的链接(多边)的网络进行分析。多节点多重网络通常被称为

meta-networks or high-dimensional networks. In contrast, SNA statistical tools focus on single or at most two mode data and facilitate the analysis of only one type of link at a time.

meta-networks or high-dimensional networks. In contrast, SNA statistical tools focus on single or at most two mode data and facilitate the analysis of only one type of link at a time.

'''元网络 Meta-Network'''或'''高维网络 High-Dimensional Networks'''。相比之下，SNA统计工具侧重于单一模式或至多两种模式的数据，一次只便于分析一种类型的链接。

DNA statistical tools tend to provide more measures to the user, because they have measures that use data drawn from multiple networks simultaneously. Latent space models (Sarkar and Moore, 2005)<ref name="social"/> and agent-based simulation are often used to examine dynamic social networks (Carley et al., 2009).<ref name="Etiology"/> From a computer simulation perspective, nodes in DNA are like atoms in quantum theory, nodes can be, though need not be, treated as probabilistic. Whereas nodes in a traditional SNA model are [[wikt:static|static]], nodes in a DNA model have the ability to learn. Properties change over time; nodes can adapt: A company's employees can learn new skills and increase their value to the network; or, capture one terrorist and three more are forced to improvise. Change propagates from one node to the next and so on. DNA adds the element of a network's evolution and considers the circumstances under which change is likely to occur.

DNA statistical tools tend to provide more measures to the user, because they have measures that use data drawn from multiple networks simultaneously. Latent space models (Sarkar and Moore, 2005) and agent-based simulation are often used to examine dynamic social networks (Carley et al., 2009). From a computer simulation perspective, nodes in DNA are like atoms in quantum theory, nodes can be, though need not be, treated as probabilistic. Whereas nodes in a traditional SNA model are static, nodes in a DNA model have the ability to learn. Properties change over time; nodes can adapt: A company's employees can learn new skills and increase their value to the network; or, capture one terrorist and three more are forced to improvise. Change propagates from one node to the next and so on. DNA adds the element of a network's evolution and considers the circumstances under which change is likely to occur.

DNA统计工具倾向于为用户提供更多的测量方法，因为它们可以同时使用来自多个网络的数据。'''潜在空间模型 Latent Space Models'''(Sarkar 和 Moore，2005年)和'''基于代理的模拟 Agent-Based Simulation'''经常被用来检查动态的社会网络(Carley 等人，2009年)。从计算机仿真的角度来看，DNA中的节点就像量子理论中的原子一样，尽管不一定需要将节点视为概率的。传统SNA模型中的节点是静态的，而DNA模型中的节点具有学习能力。特性随时间变化; 节点可以随之适应: 一个公司的员工可以学习新的技能，增加他们对网络的价值; 或者，抓捕了一名恐怖分子，另外三人被迫临时合作。变化从一个节点传播到下一个节点，依此类推。DNA增加了网络进化的元素，并考虑了可能发生变化的环境。

[[Image:DynamicNetworkAnalysisExample.jpg|right|340px|thumb|
图1：An example of a multi-entity, multi-network, dynamic network diagram 多实体、多网络、动态网络图示]]

There are three main features to dynamic network analysis that distinguish it from standard social network analysis. First, rather than just using social networks, DNA looks at meta-networks. Second, agent-based modeling and other forms of simulations are often used to explore how networks evolve and adapt as well as the impact of interventions on those networks. Third, the links in the network are not binary; in fact, in many cases they represent the probability that there is a link.

There are three main features to dynamic network analysis that distinguish it from standard social network analysis. First, rather than just using social networks, DNA looks at meta-networks. Second, agent-based modeling and other forms of simulations are often used to explore how networks evolve and adapt as well as the impact of interventions on those networks. Third, the links in the network are not binary; in fact, in many cases they represent the probability that there is a link.

动态网络分析与标准社会网络分析相比，有三个主要特征。首先，DNA研究的不仅仅是社交网络，而是元网络。其次，基于代理的建模和其他形式的模拟常用于探索网络如何演变和适应以及干预对这些网络的影响。第三，网络中的链接不是二进制的; 事实上，在许多情况下，它们代表了链接存在的概率。

==Meta-network 元网络==

A meta-network is a multi-mode, multi-link, multi-level network. Multi-mode means that there are many types of nodes; e.g., nodes people and locations. Multi-link means that there are many types of links; e.g., friendship and advice. Multi-level means that some nodes may be members of other nodes, such as a network composed of people and organizations and one of the links is who is a member of which organization.

A meta-network is a multi-mode, multi-link, multi-level network. Multi-mode means that there are many types of nodes; e.g., nodes people and locations. Multi-link means that there are many types of links; e.g., friendship and advice. Multi-level means that some nodes may be members of other nodes, such as a network composed of people and organizations and one of the links is who is a member of which organization.

'''元网络 Meta-Network'''是一个多模式、多链路、多层次的网络。多模式意味着有许多类型的节点; 例如，人和位置。多链接意味着有许多类型的链接，例如，友谊和建议。多层级意味着某些节点可能是其他节点的成员，例如由人员和组织组成的网络，而链接之一就是谁是哪个组织的成员。

While different researchers use different modes, common modes reflect who, what, when, where, why and how. A simple example of a meta-network is the PCANS formulation with people, tasks, and resources.<ref name="pcans"/> A more detailed formulation considers people, tasks, resources, knowledge, and organizations.<ref name="smartAgents"/> The ORA tool was developed to support meta-network analysis.<ref name="toolkit" />

While different researchers use different modes, common modes reflect who, what, when, where, why and how. A simple example of a meta-network is the PCANS formulation with people, tasks, and resources. A more detailed formulation considers people, tasks, resources, knowledge, and organizations. The ORA tool was developed to support meta-network analysis.

虽然不同的研究人员使用不同的模式，共同的模式却都反映了谁，什么，什么时候，在哪里，为什么和如何。元网络的一个简单示例是包含人、任务和资源的 PCANS 公式。更详细的公式考虑人员、任务、资源、知识和组织。ORA工具是为支持元网络分析而开发的。

==Illustrative problems that people in the DNA area work on DNA领域的人们正在研究的说明性问题==

* Developing metrics and statistics to assess and identify change within and across networks.
开发度量和统计数据，以评估和识别网络内部和网络之间的变化。

* Developing and validating simulations to study network change, evolution, adaptation, decay. See [[Computer simulation and organizational studies]]
开发和验证仿真以研究网络的变化，演变，适应性，衰减。

* Developing and testing theory of network change, evolution, adaptation, decay<ref>{{cite journal|author=Majdandzic, A.|title=Spontaneous recovery in dynamical networks|journal=Nature Physics|volume=10|pages=34–38|year=2013|doi=10.1038/nphys2819|display-authors=etal}}</ref>
网络变化，演化，适应，衰减的开发和测试理论

* Developing and validating formal models of network generation and evolution
开发和验证网络生成和演化的正式模型

* Developing techniques to visualize network change overall or at the node or group level
开发技术以可视化整体或节点或组级别的网络变化

* Developing statistical techniques to see whether differences observed over time in networks are due to simply different samples from a distribution of links and nodes or changes over time in the underlying distribution of links and nodes
开发统计技术，以了解随着时间的推移，在网络中观察到的差异是否仅仅是因为链接和节点分布的样本不同，还是因为链接和节点的底层分布随时间的变化

* Developing control processes for networks over time
在时间维度上，为网络开发控制过程

* Developing algorithms to change distributions of links in networks over time
在时间维度上，开发算法来改变网络中的链接分布

* Developing algorithms to track groups in networks over time
在时间维度上，开发算法来跟踪网络中的群体

* Developing tools to extract or locate networks from various data sources such as texts
开发从各种数据源(如文本)中提取或定位网络的工具

* Developing statistically valid measurements on networks over time
在时间维度上，在网络上开发有效的统计度量

* Examining the robustness of network metrics under various types of missing data
检查网络指标在不同类型缺失数据下的鲁棒性

* Empirical studies of multi-mode multi-link multi-time period networks
多模式、多链路、多时段网络的实证研究

* Examining networks as probabilistic time-variant phenomena
检验网络的概率时变现象

* Forecasting change in existing networks
预测现有网络的变化

* Identifying trails through time given a sequence of networks
在给定网络序列的时间内识别路径

* Identifying changes in node criticality given a sequence of networks anything else related to multi-mode multi-link multi-time period networks
在给定的网络序列中识别节点临界性的变化，任何与多模式、多链路、多时段网络相关的东西

* Studying random walks on temporal networks<ref name="rw" />
研究时间网络上的随机游动

* Quantifying structural properties of contact sequences in dynamic networks, which influence dynamical processes<ref name="betweenness"/>
动态网络中影响动态过程的接触序列结构特性的量化

*Assessment of covert activity<ref name="covert" /> and dark networks<ref name="dark" />
秘密活动的评估

*Citational analysis<ref name="citation" />
引文分析

*Social media analysis<ref name="socialmedia" />
社交媒体分析

*Assessment of public health systems<ref name="health" />
公共卫生系统的评估

*Analysis of hospital safety outcomes<ref name="hospital" />
医院安全结果分析

*Assessment of the structure of ethnic violence from news data<ref name="ethnic" />
从新闻数据中评估种族暴力的结构

*Assessment of terror groups<ref name="terror" />
对恐怖组织的评估

*Online social decay of social interactions<ref name="socialdecay" />
社交互动的在线社交衰退

*Visualization of large financial networks over time<ref name="dnb" />
大型金融网络随时间的可视化

*Modelling of classroom interactions in schools<ref name="edu" />
学校课堂互动的建模

== See also ==

* [[Graph dynamical system]]
图动态系统

* [[International Network for Social Network Analysis]]
国际社交网络的分析

* [[Kathleen M. Carley]]
凯瑟琳·卡利

* [[Network dynamics]]
网络动力学

* [[Network science]]
网络科学

* [[Sequential dynamical system]]ios13.3 deca mield(8)
顺序动力学系统

==References==

{{Reflist|refs=

{{Reflist|refs=

{通货再膨胀 | 参考文献

<ref name="pcans">David Krackhardt and Kathleen M. Carley, 1998, "A PCANS Model of Structure in Organization," In proceedings of the 1998 International Symposium on Command and Control Research and Technology, Monterey, CA, June 1998, Evidence Based Research, Vienna, VA, Pp. 113-119.</ref>

<ref name="smartAgents">Kathleen M. Carley, 2002, "Smart Agents and Organizations of the Future," The Handbook of New Media. Edited by Leah Lievrouw and Sonia Livingstone (Eds.), Thousand Oaks, CA, Sage, Ch. 12: 206-220.</ref>

<ref name="rw">Michele Starnini, Andrea Baronchelli, Alain Barrat, 2012, Random walks on temporal networks. Phys. Rev. E 85, 056115, http://link.aps.org/doi/10.1103/PhysRevE.85.056115</ref>

<ref name="betweenness">René Pfitzner, Ingo Scholtes, Antonios Garas, Claudio Juan Tessone, Frank Schweitzer, 2012, "Betweenness Preference: Quantifying Correlations in the Topological Dynamics of Temporal Networks", Physical Review Letters, Vol. 110, May 10, 2013.</ref>

<ref name="social">Purnamrita Sarkar and Andrew W. Moore. 2005. Dynamic social network analysis using latent space models. SIGKDD Explor. Newsl. 7, 2 (December 2005), 31-40.</ref>

<ref name="covert">Carley, Kathleen M., Michael K., Martin and John P. Hancock, 2009, "Dynamic Network Analysis Applied to Experiments from the Decision Architectures Research Environment," Advanced Decision Architectures for the Warfigher: Foundation and Technology, Ch. 4.</ref>

<ref name="Etiology">Kathleen M. Carley, Michael K. Martin and Brian Hirshman, 2009, "The Etiology of Social Change," Topics in Cognitive Science, 1.4:621-650</ref>

<ref name="dark">Everton, Sean, 2012, Disrupting Dark Networks, Cambridge University Press, New York, NY</ref>

<ref name="citation">Kas, Miray, Kathleen M. Carley and L. Richard Carley, 2012, "Who was Where, When? Spatiotemporal Analysis of Researcher Mobility in Nuclear Science," In proceedings of the International Workshop on Spatio Temporal data Integration and Retrieval (STIR 2012), held in conjunction

<ref name="citation">Kas, Miray, Kathleen M. Carley and L. Richard Carley, 2012, "Who was Where, When? Spatiotemporal Analysis of Researcher Mobility in Nuclear Science," In proceedings of the International Workshop on Spatio Temporal data Integration and Retrieval (STIR 2012), held in conjunction

Miray，Kathleen m. Carley and l. Richard Carley，2012，“ Who was Where，When？核科学中研究人员流动性的时空分析” ，在国际时空数据整合与检索研讨会(STIR，2012)的会议记录中，同时举行

with ICDE 2012, April 1, 2012, Washington D.C.</ref>

with ICDE 2012, April 1, 2012, Washington D.C.</ref>

2012，April 1,2012，Washington d.c. / ref

<ref name="terror">Kenney, Michael J., John Horgan, Cale Horne, Peter Vining, Kathleen M. Carley, Michael Bigrigg, [[Mia Bloom]], Kurt Braddock, 2012, Organizational adaptation in an activist network: Social networks, leadership, and change in al-Muhajiroun, Applied Ergonomics, 44(5):739-747.</ref>

<ref name="health">Merrill, Jacqueline, Mark G. Orr, Christie Y. Jeon, Rosalind V. Wilson, Jonathan Storrick and Kathleen M. Carley, 2012, "Topology of Local Health Officials’ Advice Networks: Mind the Gaps," Journal of Public Health Management Practice, 18(6): 602–608</ref>

<ref name="ethnic">Van Holt, Tracy, Jeffrey C. Johnson, Jamie Brinkley, Kathleen M. Carley and Janna Caspersen, 2012, "Structure of ethnic violence in Sudan: an automated content, meta-network and geospatial analytical approach," Computational and Mathematical Organization Theory, 18:340-355.</ref>

<ref name="hospital">Effken, Judith A.,Sheila Gephart and Kathleen M. Carley, 2013, "Using ORA to Assess the Relationship of Handoffs to Quality and Safety Outcomes," Computers, Informatics, Nursing. 31(1): 36-44.</ref>

<ref name="socialmedia">Carley, Kathleen. M., Jürgen Pfeffer, [[Huan Liu]], Fred Morstatter, Rebecca Goolsby, 2013, Near Real Time Assessment of Social Media Using Geo-Temporal Network Analytics, In Proceedings of 2013 IEEE/ACM International Conference on Advances in Social Networks Analysis and Mining (ASONAM), August 25–28, 2013, Niagara Falls, Canada.</ref>

<ref name="toolkit">Kathleen M. Carley. 2014. "ORA: A Toolkit for Dynamic Network Analysis and Visualization," In Reda Alhajj and Jon Rokne (Eds.) Encyclopedia of Social Network Analysis and Mining, Springer.</ref>

<ref name="socialdecay">M. Abufouda, K. A. Zweig ."A Theoretical Model for Understanding the Dynamics of Online Social Networks Decay". arXiv preprint arXiv:1610.01538.</ref>

<ref name="dnb">{{cite journal|last1=Heijmans|first1=Ronald|last2=Heuver|first2=Richard|last3=Levallois|first3=Clement|last4=van Lelyveld|first4=Iman|title=Dynamic visualization of large financial networks|journal=The Journal of Network Theory in Finance|volume=2|issue=2|year=2016|pages=57–79|issn=2055-7795|doi=10.21314/JNTF.2016.017}}</ref>

<ref name="edu">Christian Bokhove, 2016, "Exploring classroom interaction with dynamic social network analysis", International Journal of Research & Method in Education, doi:10.1080/1743727X.2016.1192116.</ref>

}}

}}

}}

== Further reading ==

*Kathleen M. Carley, 2003, "Dynamic Network Analysis" in Dynamic Social Network Modeling and Analysis: Workshop Summary and Papers, Ronald Breiger, Kathleen Carley, and Philippa Pattison, (Eds.) Committee on Human Factors, National Research Council, National Research Council. Pp. 133–145, Washington, DC.

*Kathleen M. Carley, 2002, "Smart Agents and Organizations of the Future" The Handbook of New Media. Edited by Leah Lievrouw and Sonia Livingstone, Ch. 12, pp. 206–220, Thousand Oaks, CA, Sage.

*Kathleen M. Carley, Jana Diesner, Jeffrey Reminga, Maksim Tsvetovat, 2008, Toward an Interoperable Dynamic Network Analysis Toolkit, DSS Special Issue on Cyberinfrastructure for Homeland Security: Advances in Information Sharing, Data Mining, and Collaboration Systems. [http://www.sciencedirect.com/science/journal/01679236 Decision Support Systems] 43(4):1324-1347 ([http://www.sciencedirect.com/science?_ob=ArticleURL&_udi=B6V8S-4KGG5P7-1&_user=4422&_coverDate=08%2F31%2F2007&_rdoc=20&_fmt=high&_orig=browse&_srch=doc-info(%23toc%235878%232007%23999569995%23665759%23FLA%23display%23Volume)&_cdi=5878&_sort=d&_docanchor=&_ct=52&_acct=C000059600&_version=1&_urlVersion=0&_userid=4422&md5=9459e84d7a8863039c7abd5065266250 article 20]{{dead link|date=March 2019|bot=medic}}{{cbignore|bot=medic}})

* Dan Braha and Yaneer Bar-Yam, 2006, [https://static1.squarespace.com/static/5b68a4e4a2772c2a206180a1/t/5c5def5124a694e75e6109bc/1549659985911/Theory_Time_Dependent.pdf "Time-Dependent Complex Networks."]

*Terrill L. Frantz, Kathleen M. Carley. 2009, Toward A Confidence Estimate For The Most-Central-Actor Finding. Academy of Management Annual Conference, Chicago, IL, USA, 7–11 August. (Awarded the Sage Publications/RM Division Best Student Paper Award)

*Petter Holme, Jari Saramäki, 2011, "Temporal networks". https://arxiv.org/abs/1108.1780

*C. Aggarwal, K. Subbian, 2014, "Evolutionary Network Analysis: A Survey". ACM Computing Surveys, 47(1). ([http://charuaggarwal.net/CSUR-2013-0157.pdf pdf])

== External links ==

* [http://www.eecs.harvard.edu/%7Eparkes/RadcliffeSeminar.htm Radcliffe Exploratory Seminar on Dynamic Networks]

* [http://www.casos.cs.cmu.edu/ Center for Computational Analysis of Social and Organizational Systems (CASOS)]

{{Social networking}}

{{DEFAULTSORT:Dynamic Network Analysis}}

[[Category:Computer network analysis]]

Category:Computer network analysis

类别: 计算机网络分析

[[Category:Social statistics]]

Category:Social statistics

类别: 社会统计

[[Category:Methods in sociology]]

Category:Methods in sociology

范畴: 社会学方法

<noinclude>

This page was moved from [[wikipedia:en:Dynamic network analysis]]. Its edit history can be viewed at [[动态网络分析/edithistory]]</noinclude>

[[Category:待整理页面]]

因果推断

2020-09-18T20:08:37Z

Zc1234567：

{{short description|Branch of statistics concerned with inferring causal relationships between variables}}

{{Expert needed|date=October 2019}}

'''Causal inference''' is the process of drawing a conclusion about a [[causal]] connection based on the conditions of the occurrence of an effect. The main difference between causal inference and inference of [[association (statistics)|association]] is that the former analyzes the response of the effect variable when the cause is changed.<ref name=Pearl_Journal>{{cite journal|last=Pearl|first=Judea|title=Causal inference in statistics: An overview|journal=Statistics Surveys|date=1 January 2009|volume=3|issue=|pages=96–146|doi=10.1214/09-SS057|url=http://ftp.cs.ucla.edu/pub/stat_ser/r350.pdf}}</ref><ref name=Morgan_book>{{cite book|last=Morgan|first=Stephen|author2=Winship, Chris|title=Counterfactuals and Causal inference|publisher=Cambridge University Press|year=2007|isbn=978-0-521-67193-4}}</ref> The science of why things occur is called [[etiology]]. Causal inference is an example of [[causal reasoning]].

'''因果推断Causal inference'''是根据某一效应发生的条件得出关于因果关系的结论的过程。因果推断与'''关联推理inference of association'''的主要区别在于前者分析在原因变化时结果变量的反应。研究事情为什么发生的科学叫做'''病因学etiology'''。因果推断是'''因果推理causal reasoning'''的一个例子。

--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“是根据某一效应发生的条件得出关于因果关系的结论的过程。”一句中的“根据”改为“基于”，“效应”改为“事件”，“因果关系的结论”改为“因果联系结论”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“的主要区别在于前者分析在原因变化时结果变量的反应。”一句中“在原因变化时”改为“了当原因改变时”,“反应”改为“响应”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“研究事情为什么发生的科学叫做”一句改为“研究事件因何而起的科学被称为”

==Definition定义==

Inferring the [[cause]] of something has been described as:

'''对某事原因的推断过程已经被描述为是:Inferring the [[cause]] of something has been described as:'''

--[[用户:嘉树|嘉树]]（[[用户讨论:嘉树|讨论]]） inferring是ing形式，因此译为“推断的过程”，存疑
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“对某事原因的推断过程已经被描述为是：”一句改为“推断某事原因的过程被描述为：”

*"...reason[ing] to the conclusion that something is, or is likely to be, the cause of something else".<ref name=EB>{{cite web|title=causal inference|url=http://www.britannica.com/EBchecked/topic/1442615/causal-inference|publisher=Encyclopædia Britannica, Inc.|accessdate=24 August 2014}}</ref>

*“推理得出某事是（或可能是）其他事情的原因这一结论的过程。”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“推理得出某事是（或可能是）其他事情的原因这一结论的过程。”一句改为“某事是（或可能是）其他事情的原因这一结论。”
*"Identification of the cause or causes of a phenomenon, by establishing covariation of cause and effect, a time-order relationship with the cause preceding the effect, and the elimination of plausible alternative causes."<ref name=psy>{{cite book|author1=John Shaughnessy|author2=Eugene Zechmeister|author3=Jeanne Zechmeister|title=Research Methods in Psychology|date=2000|publisher=McGraw-Hill Humanities/Social Sciences/Languages|isbn=978-0077825362|pages=Chapter 1 : Introduction|url=http://www.mhhe.com/socscience/psychology/shaugh/ch01_concepts.html|accessdate=24 August 2014|archive-url=https://web.archive.org/web/20141015135541/http://www.mhhe.com/socscience/psychology/shaugh/ch01_concepts.html|archive-date=15 October 2014|url-status=dead}}</ref>

*“通过建立因果的共变关系、建立原因先于结果的时间顺序关系，以及消除其他可能的替代原因的过程，从而对现象的一个或多个原因进行确定的过程。”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“通过建立因果的共变关系、建立原因先于结果的时间顺序关系，以及消除其他可能的替代原因的过程，从而对现象的一个或多个原因进行确定的过程。”一句改为“通过建立因果的共变模型，前因后果的时间顺序联系，以及消除其他可能的替代原因，从而对现象的一个或多个原因进行确认。”
==Methods 方法==

Epidemiological studies employ different [[epidemiological method]]s of collecting and measuring evidence of risk factors and effect and different ways of measuring association between the two. A [[hypothesis]] is formulated, and then [[Statistical hypothesis testing|tested with statistical methods]]. It is [[statistical inference]] that helps decide if data are due to chance, also called [[random variation]], or indeed correlated and if so how strongly. However, [[correlation does not imply causation]], so further methods must be used to infer causation.{{Citation needed|date=May 2019}}

'''流行病学epidemiological'''收集和衡量危险因素和结果，以及衡量危险因素和结果之间关系的方法与其他学科不同。一个假设提出来以后用'''统计学假设检验Statistical hypothesis testing'''。这种'''统计学推断statistical inference '''有助于判断数据是由偶然性引起的，也就是'''随机变异random variation'''，还是确实存在相关性，以及相关性有多强。然而，相关不意味着因果，因此必须进一步使用其他方法来推断因果关系。
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“收集和衡量危险因素和结果，以及衡量危险因素和结果之间关系的方法与其他学科不同。一个假设提出来以后用”一句改为“运用不同的流行病模型来收集和衡量危险因素和结果，以及判定两者之间的联系”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“一个假设提出来以后”一句改为“一个假说被提出来后”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“是由偶然性引起的，也就是”一句改为“是否由偶然性引起，也被称为”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“还是确实存在相关性，以及相关性有多强”一句改为“还是确实相关以及相关性的强弱”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“因此必须进一步使用其他方法来推断因果关系”一句改为“必须使用其他方法来推断其因果关系”
Common frameworks for causal inference are [[structural equation modeling]] and the [[Rubin causal model]].{{citation needed|date=August 2014}}

因果推断的常见框架有'''结构方程模型structural equation modeling'''和'''Rubin因果模型 Rubin causal model'''。

--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“因果推断的常见框架”一句改为“常见的因果推断框架有”
==In epidemiology 在流行病学中==

[[Epidemiology]] studies patterns of health and disease in defined populations of [[living beings]] in order to [[infer]] causes and effects. An association between an [[Exposure (environmental hazard)|exposure]] to a putative [[risk factor]] and a disease may be suggestive of, but is not equivalent to causality because [[correlation does not imply causation]]. Historically, [[Koch's postulates]] have been used since the 19th century to decide if a microorganism was the cause of a disease. In the 20th century the [[Bradford Hill criteria]], described in 1965<ref name="bh65">{{cite journal |last=Hill |first=Austin Bradford |year=1965 |title=The Environment and Disease: Association or Causation? |journal=[[Proceedings of the Royal Society of Medicine]] |volume=58 |pages=295–300 |url=http://www.edwardtufte.com/tufte/hill |pmid=14283879 |pmc=1898525 |issue=5 |doi=10.1177/003591576505800503}}</ref> have been used to assess causality of variables outside microbiology, although even these criteria are not exclusive ways to determine causality.

'''流行病学Epidemiology'''研究特定生物群体的健康和疾病'''模式patterns'''，以推断原因和结果。'''暴露exposure '''于一般认为的'''危险因素risk factor'''和疾病之间的联系可能被提出，但不等同于确认因果关系，因为相关不意味着因果。从历史上看，'''科赫法则 Koch's postulates'''从19世纪开始就被用来判断一种微生物是否是一种疾病的原因。在20世纪，'''布拉德福德·希尔准则Bradford Hill criteria'''（参见Bradford Hill 1965年的文章<ref name="bh65"></ref>中）已经被用来评估微生物学之外的变量的因果关系，尽管即使是这些标准也不是确定因果关系的唯一方法。

--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“的联系可能被提出，但不等同于确认因果关系”一句改为，“可能存在关联，但不等于确定因果关系”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“从19世纪开始”将此短语提至“科赫法则”之前。
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“疾病的原因”一词改为“疾病病因”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“尽管即使是这些标准也不是确定因果关系的唯一方法”一句中去掉“即使”

In [[molecular epidemiology]] the phenomena studied are on a [[molecular biology]] level, including genetics, where [[biomarkers]] are evidence of cause or effects.

'''分子流行病学molecular epidemiology'''中研究的现象是在'''分子生物学'''水平上的，也涵盖了遗传学。而遗传学中的'''生物标志物biomarkers'''就是原因或结果的证据。

--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“分子生物学”一词改成“生物分子”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“水平上的，也涵盖了遗传学。而遗传学中的”一句改为“水平上也涵盖了遗传学，而其中”

A recent trend{{when|date=August 2014}} is to identify [[evidence]] for influence of the exposure on [[molecular pathology]] within diseased [[Tissue (biology)|tissue]] or cells, in the emerging interdisciplinary field of [[molecular pathological epidemiology]] (MPE).{{third-party-inline|date=August 2014}} Linking the exposure to molecular pathologic signatures of the disease can help to assess causality. {{third-party-inline|date=August 2014}} Considering the inherent nature of [[heterogeneity]] of a given disease, the unique disease principle, disease phenotyping and subtyping are trends in biomedical and [[public health]] sciences, exemplified as [[personalized medicine]] and [[precision medicine]].{{third-party-inline|date=August 2014}}

在新兴的'''分子病理流行病学molecular pathological epidemiology (MPE)'''交叉学科领域，最近的一个趋势（截至2014年）是确定在病变组织或细胞内，'''暴露exposure '''在'''分子病理学molecular pathology'''上的影响。将暴露与疾病的分子病理特征联系起来可以帮助因果关系的评估。鉴于给定疾病的'''异质性'''的固有特征、独特的疾病原理等，疾病'''表现型phenotyping'''和'''亚型subtyping '''现在是生物医学和'''公共卫生科学public health'''的趋势，例证包括'''个体化医学personalized medicine'''和'''精准医学precision medicine'''等。

--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“暴露”改为“暴露迹象”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“上的影响”改为“影响的证据”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“将暴露”改为“将暴露迹象”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“因果关系的评估”改为“评估因果关系”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“给定疾病的”改为“特定疾病”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“独特的疾病原理等”改为“罕见的病理”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“现在是生物医学和”改为“是生物医学和”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“个体化医学”改为“私人医疗”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“精准医学”改为“精密医学”
==In computer science在计算机科学领域==

Determination of cause and effect from joint observational data for two time-independent variables, say X and Y, has been tackled using asymmetry between evidence for some model in the directions, X → Y and Y → X. The primary approaches are based on [[Algorithmic information theory]] models and noise models.{{Citation needed|date=May 2019}}

确定两个时间独立变量：X 和 Y 的联合观测数据因果关系的问题已经被解决了，方法是利用 X → Y 和 Y → X 方向上某些模型的证据不对称性。主要的方法基于'''算法信息理论Algorithmic information theory'''模型和'''噪声模型noise models'''。

--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“确定两个时间独立变量：X 和 Y 的联合观测数据因果关系的问题已经被解决了，方法是利用 X → Y 和 Y → X 方向上某些模型的证据不对称性。”改为“由两个时间自变量，例如X,Y；联合观测数据来确定因果关系。已经被使用一些模型方向上证据的不对称性给解决了，例如：X → Y 和 Y → X 。”

===Algorithmic information models算法信息模型===

Compare two programs, both of which output both X and Y.

比较两个同时输出 X 和 Y 的程序。
* Store Y and a compressed form of X in terms of uncompressed Y.

* Store X and a compressed form of Y in terms of uncompressed X.

* 用未压缩的 X 来存储 X 和压缩形式的 Y 。

--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“用未压缩的 X 来存储 X 和压缩形式的 Y ”改为“根据未压缩的Y存储Y和X的压缩型，根据未压缩的X存储X和Y的压缩型”

The shortest such program implies the uncompressed stored variable more-likely causes the computed variable.<ref>Kailash Budhathoki and Jilles Vreeken "[http://eda.mmci.uni-saarland.de/pubs/2016/origo-budhathoki,vreeken.pdf Causal Inference by Compression]" 2016 IEEE 16th International Conference on Data Mining (ICDM)</ref><ref>{{Cite journal |doi = 10.1007/s10115-018-1286-7|title = Telling cause from effect by local and global regression|journal = Knowledge and Information Systems|year = 2018|last1 = Marx|first1 = Alexander|last2 = Vreeken|first2 = Jilles|volume=60|issue = 3|pages=1277–1305|doi-access = free}}</ref>

最短的这种程序意味着，更有可能是未压缩的'''存储变量stored variable'''导致了'''计算出的变量computed variable'''。

--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“最短的这种程序意味着”改为“最短的此类程序表明”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“计算出的变量”改为“计算变量”

===Noise models噪音模型===

Incorporate an independent noise term in the model to compare the evidences of the two directions.

在模型中引入一个独立的噪声项，以比较两个方向的证据。

Here are some of the noise models for the hypothesis Y → X with the noise E:

下面是一些支持 Y → X 假设且具有噪声 E 的噪声模型:
* Additive noise:<ref>Hoyer, Patrik O., et al. "[https://papers.nips.cc/paper/3548-nonlinear-causal-discovery-with-additive-noise-models.pdf Nonlinear causal discovery with additive noise models]." NIPS. Vol. 21. 2008.</ref> <math>Y = F(X)+E</math>
* '''加法噪音Additive noise'''

* Linear noise:<ref>{{cite journal | last1 = Shimizu | first1 = Shohei | display-authors = etal | year = 2011 | title = DirectLiNGAM: A direct method for learning a linear non-Gaussian structural equation model | url = http://www.jmlr.org/papers/volume12/shimizu11a/shimizu11a.pdf | journal = The Journal of Machine Learning Research | volume = 12 | issue = | pages = 1225–1248 }}</ref> <math>Y = pX + qE</math>
* '''线性噪音Linear noise'''

* Post-non-linear:<ref>Zhang, Kun, and Aapo Hyvärinen. "[https://arxiv.org/pdf/1205.2599 On the identifiability of the post-nonlinear causal model]." Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence. AUAI Press, 2009.</ref> <math>Y = G(F(X)+E)</math>
* '''后非线性Post-non-linear（噪音）'''

* Heteroskedastic noise: <math>Y = F(X)+E.G(X)</math>
* '''异方差噪音Heteroskedastic noise'''

* Functional noise:<ref name="Mooij">Mooij, Joris M., et al. "[http://papers.nips.cc/paper/4173-probabilistic-latent-variable-models-for-distinguishing-between-cause-and-effect.pdf Probabilistic latent variable models for distinguishing between cause and effect]." NIPS. 2010.</ref> <math>Y = F(X,E)</math>
* '''功能性噪音Functional noise'''

The common assumption in these models are:

这些模型的共同假设是:
* There are no other causes of Y.
* Y 没有其他原因。

* X and E have no common causes.
* X 和 E 没有共同的原因。

* Distribution of cause is independent from causal mechanisms.
* 原因的分布独立于因果机制。

On an intuitive level, the idea is that the factorization of the joint distribution P(Cause, Effect) into P(Cause)*P(Effect | Cause) typically yields models of lower total complexity than the factorization into P(Effect)*P(Cause | Effect). Although the notion of “complexity” is intuitively appealing, it is not obvious how it should be precisely defined.<ref name="Mooij"/> A different family of methods attempt to discover causal "footprints" from large amounts of labeled data, and allow the prediction of more flexible causal relations.<ref>Lopez-Paz, David, et al. "[http://www.jmlr.org/proceedings/papers/v37/lopez-paz15.pdf Towards a learning theory of cause-effect inference]" ICML. 2015</ref>

在直观的层面上，这个想法是联合分布P(Cause, Effect) 到 P(Cause)*P(Effect | Cause)的因式分解通常产生的模型的总'''复杂性complexity '''低于到P(Effect)*P(Cause | Effect)的因式分解。尽管“复杂性”的概念在直觉上很吸引人，但是对于如何定义它却并不显而易见。另一种不同类族的方法尝试从大量标签过的数据中发现因果的“足迹”，并且允许预测更灵活的因果关系。
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“这个想法是联合分布P(Cause, Effect) 到 P(Cause)*P(Effect | Cause)的因式分解通常产生的模型的总”改为“联合分布P(起因,结果)到P(起因)*P(结果|起因)拆分的主意通常产生模型的总”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“低于到P(Effect)*P(Cause | Effect)的因式分解”改为“低于将P(起因,结果)到P(结果)*P(起因|结果)的拆分”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“但是对于如何定义”改为“但对于应该如何精确定义”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“标签过”改为“被标记”

== In statistics and economics 在统计学和经济学领域==

{{Main|Causality#Statistics and economics}}

--[[用户:嘉树|嘉树]]（[[用户讨论:嘉树|讨论]]）本段似有错漏，英文词条和本段内容有一些不同。因此，（1）先写本段的翻译，（2）再写英文词条中有不同的地方，（3）最后整合一下。【】括起来的是在两个版本中需要照应和修改的部分。

In [[statistics]] and [[economics]], causality is often tested via [[regression analysis]]. Several methods can be used to distinguish actual causality from spurious correlations. First, economists constructing regression models establish the direction of causal relation based on economic theory (theory-driven econometrics). For example, if one studies the dependency between rainfall and the future price of a commodity, then theory (broadly construed) indicates that rainfall can influence prices, but futures prices cannot make changes to the amount of rain<ref>{{Cite book|last=Simon|first=Herbert|title=Models of Discovery|publisher=Springer|year=1977|location=Dordrecht|page=52}}</ref> . Second, the [[instrumental variables]] (IV) technique may be employed to remove any reverse causation by introducing a role for other variables (instruments) that are known to be unaffected by the dependent variable. Third, economists consider time precedence to choose appropriate model specification. Given that partial correlations are symmetrical, one cannot determine the direction of causal relation based on correlations only. Based on the notion of probabilistic view on causality, economists assume that causes must be prior in time than their effects. This leads to using the variables representing phenomena happening earlier as independent variables and developing econometric tests for causality (e.g., Granger-causality tests) applicable in time series analysis<ref>{{Cite book|last=Maziarz|first=Mariusz|title=The Philosophy of Causality in Economics: Causal Inferences and Policy Proposals|publisher=Routledge|year=2020|location=New York}}</ref>. Fifth, other regressors are included to ensure that [[confounding variable]]s are not causing a regressor to appear to be significant spuriously but, in the areas suffering from the problem of multicollinearity such as macroeconomics, it is in principle impossible to include all confounding factors and therefore econometric models are susceptible to the common-cause fallacy.<ref>{{Cite journal|last=Henschen|first=Tobias|date=2018|title=The in-principle inconclusiveness of causal evidence in macroeconomics|journal=European Journal for Philosophy of Science|volume=8|pages=709–733}}</ref>. Recently, the movement of design-based econometrics has popularized using natural experiments and quasi-experimental research designs to address the problem of spurious correlations.<ref>{{Cite book|last=Angrist Joshua & Pischke Jörn-Steffen|title=Mostly Harmless Econometrics: An Empiricist's Companion|publisher=Princeton University Press|year=2008|location=Princeton}}</ref>

在统计学和经济学中，因果关系通常通过回归分析来检验。有几种方法可以用来区分真实的因果关系和虚假的相关性。第一，经济学家根据经济理论('''理论驱动theory-driven'''的计量经济学)构建回归模型，从而确定因果关系的方向。
例如，如果研究降雨与未来商品价格之间的依赖关系，那么一个广义上建构的理论表明，降雨可以影响价格，但未来价格不能改变降雨量。<ref>{{Cite book|last=Simon|first=Herbert|title=Models of Discovery|publisher=Springer|year=1977|location=Dordrecht|page=52}}</ref> . 第二，'''工具变量instrumental variables(IV)'''技术可以通过引入其他已知不受因变量的影响的工具变量来消除任何反向因果关系。【第三，经济学家会考虑时间优先级来选择合适的具体模型。由于'''偏相关partial correlations'''是对称的，人们不能在相关的基础上确定因果关系的方向。经济学家基于因果关系的'''概率观点probabilistic view'''假设，原因必须在时间上优先于其结果。这导致经济学家使用较早发生的现象作为自变量，并开发适用于时间序列分析的因果关系检验计量经济方法（例如，'''格兰杰因果检验'''）<ref>{{Cite book|last=Maziarz|first=Mariusz|title=The Philosophy of Causality in Economics: Causal Inferences and Policy Proposals|publisher=Routledge|year=2020|location=New York}}</ref>。第五，有些做法包括了其他回归项，从而确保'''混淆变量confounding variables'''不会导致某个回归因素显得明显虚假，但遭受'''多重共线性multicollinearity'''问题困扰的领域，如宏观经济学，原则上不可能包括所有混淆因素，因此计量经济模型容易出现'''共因谬误common-cause fallacy'''<ref>{{Cite journal|last=Henschen|first=Tobias|date=2018|title=The in-principle inconclusiveness of causal evidence in macroeconomics|journal=European Journal for Philosophy of Science|volume=8|pages=709–733}}</ref>。近年来，'''以研究设计为基础的计量经济学design-based econometrics'''运动已经推广使用自然实验和准实验研究设计来解决'''虚假相关spurious correlations'''的问题<ref>{{Cite book|last=Angrist Joshua & Pischke Jörn-Steffen|title=Mostly Harmless Econometrics: An Empiricist's Companion|publisher=Princeton University Press|year=2008|location=Princeton}}</ref>。】

--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】有几种方法可以用来区分真实的因果关系和虚假的相关性。一句中的“区分”改为“鉴别”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】从而确定因果关系的方向，一句中“确定”改为“建立”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】如果研究降雨与未来商品价格之间的依赖关系，一句中“未来商品价格”改为“一种商品的未来价格
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】那么一个广义上建构的理论表明，一句中“一个”去掉。
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】技术可以通过引入其他已知不受因变量的影响的工具变量来消除任何反向因果关系。一句中“工具变量”改为“变量（工具）”；“反向因果”改为“逆因果”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】经济学家会考虑时间优先级来选择合适的具体模型。一句中“会”改为“会通过”；“合适的具体模型”改为“适当的模型规范”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“人们不能在相关的基础上确定因果关系的方向”一句改为“不能仅仅根据一方面的相关性来确定因果关系的方向”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“经济学家基于因果关系的”一句改为“基于因果关系的”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“假设，原因必须在时间上优先于其结果”一句改为“经济学家假设，在时间上原因必须先于其结果”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“并开发适用于时间序列分析的因果关系检验计量经济方法”一句中的“检验计量经济方法”改为“计量经济学的检验方法”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“不会导致某个回归因素显得明显虚假”一句中的“明显虚假”改为“过于虚假”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“但遭受”中的“但”改为“但在”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“以研究设计为基础的计量经济学”一句中“研究”去掉。
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“运动已经推广使用自然实验和准实验研究设计来解决”一句中“运动已经推广”改为“活动已经推广至”

--[[用户:嘉树|嘉树]]（[[用户讨论:嘉树|讨论]]）英文词条的第三和第四：

Third, the principle that effects cannot precede causes can be invoked, by including on the right side of the regression only variables that precede in time the dependent variable.
Fourth, other regressors are included to ensure that confounding variables are not causing a regressor to spuriously appear to be significant. Correlation by coincidence, as opposed to correlation reflecting actual dependence of the underlying process, can be ruled out by using large samples and by performing cross validation to check that correlations are maintained on data that were not used in the regression.

【第三，通过在回归的右侧只包括时间上在因变量之前的变量，就可以使用结果不能优先于原因的原则。
第四，有些方法包括了其他回归因素，以确保'''混淆变量confounding variables'''不会导致一个回归项虚假地呈现显著。通过使用大样本和交叉验证检查在回归中未使用的数据上是否保持了相关性，可以排除巧合的，而不是反映实际依赖内在过程的相关性。】

--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“通过在回归的右侧只包括时间上在因变量之前的变量”改为“在正向回归中只包含在时间上早于因变量的变量”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“就可以使用结果不能优先于原因的原则”改为“就可以引用结果不能先于原因的原则”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“有些方法包括了其他回归因素，以确保”改为“有些方法包括了其他回归因素以确保”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“不会导致一个回归项虚假地呈现显著”改为“不会导致回归项虚假地呈现这种现象十分重要”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“通过使用大样本和交叉验证检查在回归中未使用的数据上是否保持了相关性，可以排除巧合的，而不是反映实际依赖内在过程的相关性。”一句改为“通过使用大规模样本和交叉验证来检查在回归中未使用的数据是否保持了相关，这样可以排除因巧合的相关性，而不是反映实际依赖内在过程的相关性。”
--[[用户:嘉树|嘉树]]（[[用户讨论:嘉树|讨论]]）整合后的翻译：

在统计学和经济学中，因果关系通常通过回归分析来检验。有几种方法可以用来区分真实的因果关系和虚假的相关性。第一，经济学家根据经济理论('''理论驱动theory-driven'''的计量经济学)构建回归模型，从而确定因果关系的方向。例如，如果研究降雨与未来商品价格之间的依赖关系，那么一个广义上建构的理论表明，降雨可以影响价格，但未来价格不能改变降雨量。<ref>{{Cite book|last=Simon|first=Herbert|title=Models of Discovery|publisher=Springer|year=1977|location=Dordrecht|page=52}}</ref> . 第二，'''工具变量instrumental variables(IV)'''技术可以通过引入其他已知不受因变量的影响的工具变量来消除任何反向因果关系。第三，通过在回归的右侧只包括时间上在因变量之前的变量，就可以使用结果不能优先于原因的原则。由于'''偏相关partial correlations'''是对称的，人们不能在相关的基础上确定因果关系的方向。经济学家基于因果关系的'''概率观点probabilistic view'''假设，原因必须在时间上优先于其结果。这导致经济学家使用较早发生的现象作为自变量，并开发适用于时间序列分析的因果关系检验计量经济方法（例如，'''格兰杰因果检验'''）<ref>{{Cite book|last=Maziarz|first=Mariusz|title=The Philosophy of Causality in Economics: Causal Inferences and Policy Proposals|publisher=Routledge|year=2020|location=New York}}</ref>。第四，有些方法包括了其他回归因素，以确保'''混淆变量confounding variables'''不会导致一个回归项虚假地呈现显著。通过使用大样本和交叉验证检查在回归中未使用的数据上是否保持了相关性，可以排除巧合的，而不是反映实际依赖内在过程的相关性。但遭受'''多重共线性multicollinearity'''问题困扰的领域，如宏观经济学，原则上不可能包括所有混淆因素，因此计量经济模型容易出现'''共因谬误common-cause fallacy'''<ref>{{Cite journal|last=Henschen|first=Tobias|date=2018|title=The in-principle inconclusiveness of causal evidence in macroeconomics|journal=European Journal for Philosophy of Science|volume=8|pages=709–733}}</ref>。近年来，'''以研究设计为基础的计量经济学design-based econometrics'''运动已经推广使用自然实验和准实验研究设计来解决'''虚假相关spurious correlations'''的问题<ref>{{Cite book|last=Angrist Joshua & Pischke Jörn-Steffen|title=Mostly Harmless Econometrics: An Empiricist's Companion|publisher=Princeton University Press|year=2008|location=Princeton}}</ref>。

== In social science 在社会科学领域==

The social sciences have moved increasingly toward a quantitative framework for assessing causality. Much of this has been described as a means of providing greater rigor to social science methodology. Political science was significantly influenced by the publication of [[Designing Social Inquiry]], by Gary King, Robert Keohane, and Sidney Verba, in 1994. King, Keohane, and Verba (often abbreviated as KKV) recommended that researchers applying both quantitative and qualitative methods adopt the language of statistical inference to be clearer about their subjects of interest and units of analysis.<ref>{{Cite book|title=Designing social inquiry : scientific inference in qualitative research|first=Gary|last=King|date=2012|publisher=Princeton Univ. Press|isbn=978-0691034713|oclc=754613241}}</ref><ref name=":0">{{Cite journal|last=Mahoney|first=James|date=January 2010|title=After KKV|journal=World Politics|volume=62|issue=1|pages=120–147|jstor=40646193|doi=10.1017/S0043887109990220}}</ref> Proponents of quantitative methods have also increasingly adopted the [[Rubin causal model|potential outcomes framework]], developed by [[Donald Rubin]], as a standard for inferring causality.{{Citation needed|date=May 2019}}

社会科学越来越倾向评估因果关系的定量框架。框架中的很大一部分已经被描述为一种提供更严格的'''社会科学方法social science methodology'''的方式。1994年，'''加里·金Gary King'''、'''罗伯特 · 基奥汉Robert Keohane'''和'''西德尼 · 维尔巴Sidney Verba'''合著的《'''设计社会学问卷Designing Social Inquiry'''》对政治科学产生了重大影响。'''金、基奥汉，和维尔巴（通常缩写为 KKV）建议研究人员同时采用定量和定性的方法，采用统计推论的语言来更清楚地说明他们感兴趣的主题和分析的单位。King, Keohane, and Verba (often abbreviated as KKV) recommended that researchers applying both quantitative and qualitative methods adopt the language of statistical inference to be clearer about their subjects of interest and units of analysis.'''<ref>{{Cite book|title=Designing social inquiry : scientific inference in qualitative research|first=Gary|last=King|date=2012|publisher=Princeton Univ. Press|isbn=978-0691034713|oclc=754613241}}</ref><ref name=":0">{{Cite journal|last=Mahoney|first=James|date=January 2010|title=After KKV|journal=World Politics|volume=62|issue=1|pages=120–147|jstor=40646193|doi=10.1017/S0043887109990220}}</ref>定量方法的支持者也越来越多地采用'''唐纳德 · 鲁宾Donald Rubin'''开发的'''潜在结果框架potential outcomes framework'''作为推断因果关系的标准。
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“社会科学越来越倾向评估因果关系的定量框架”一句改为“社会科学越来越倾向用定量框架来评估因果关系”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“的方式”改为“的手段”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“建议研究人员同时采用定量和定性的方法，采用统计推论的语言来更清楚地说明他们感兴趣的主题和分析的单位。”改为“建议同时采用定量和定性方法的研究人员采用统计推断的语言，以便更清楚地了解他们感兴趣的主题和分析单位。”

Debates over the appropriate application of quantitative methods to infer causality resulted in increased attention to the reproducibility of studies. Critics of widely-practiced methodologies argued that researchers have engaged in [[Data dredging|P hacking]] to publish articles on the basis of spurious correlations.<ref>{{Cite news|url=https://www.nytimes.com/2017/10/18/magazine/when-the-revolution-came-for-amy-cuddy.html|title=When the Revolution Came for Amy Cuddy|last=Dominus|first=Susan|date=18 October 2017|work=The New York Times|access-date=2019-03-02|language=en-US|issn=0362-4331}}</ref> To prevent this, some have advocated that researchers preregister their research designs prior to conducting to their studies so that they do not inadvertently overemphasize a non-reproducible finding that was not the initial subject of inquiry but was found to be statistically significant during data analysis.<ref>{{Cite web|url=https://www.americanscientist.org/article/the-statistical-crisis-in-science|title=The Statistical Crisis in Science|date=6 February 2017|website=American Scientist|language=en|access-date=2019-04-18}}</ref> Internal debates about methodology and reproducibility within the social sciences have at times been acrimonious.{{Citation needed|date=May 2019}}

合适地应用定量方法来推断因果关系的相关争论导致了对研究'''可重复性reproducibility'''的更多关注。对广泛被使用的方法持批评态度的人认为，研究人员利用'''数据挖掘Data dredging'''或'''p-hacking'''技术以在虚假相关的基础上发表文章<ref>{{Cite news|url=https://www.nytimes.com/2017/10/18/magazine/when-the-revolution-came-for-amy-cuddy.html|title=When the Revolution Came for Amy Cuddy|last=Dominus|first=Susan|date=18 October 2017|work=The New York Times|access-date=2019-03-02|language=en-US|issn=0362-4331}}</ref>。为了避免这种情况的发生，一些人主张研究人员在进行研究之前'''预注册preregister'''他们的研究设计，这样他们就不会无意中过分强调一项不可复制的发现，这项发现并非最初的调查对象，但在数据分析中被发现具有统计意义<ref>{{Cite web|url=https://www.americanscientist.org/article/the-statistical-crisis-in-science|title=The Statistical Crisis in Science|date=6 February 2017|website=American Scientist|language=en|access-date=2019-04-18}}</ref>。社会科学内部关于方法论和可重复性的争论有时是尖锐的{{Citation needed|date=May 2019}}。
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“技术以在虚假相关的基础上发表文章”一句中“技术”改为“黑客技术”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“一些人主张研究人员在进行研究之前”一句中“一些人”改为“一些批评人士”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“但在数据分析中被发现具有统计意义”一句改为“而是在数据分析过程中具有统计显著性”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“社会科学内部关于方法论和可重复性的争论有时是尖锐的”一句中的“争论”改为“内部争论”；“尖锐”改为“激烈”

While much of the emphasis remains on statistical inference in the potential outcomes framework, social science methodologists have developed new tools to conduct causal inference with both qualitative and quantitative methods, sometimes called a “mixed methods” approach.<ref>{{Cite book|url=https://books.google.com/books/about/Designing_and_Conducting_Mixed_Methods_R.html?id=YcdlPWPJRBcC|title=Designing and Conducting Mixed Methods Research|last=Creswell|first=John W.|last2=Clark|first2=Vicki L. Plano|date=2011|publisher=SAGE Publications|isbn=9781412975179|language=en}}</ref><ref>{{Cite book|url=https://www.cambridge.org/core/books/multimethod-social-science/286C2742878FBCC6225E2F10D6095A0C|title=Multi-Method Social Science by Jason Seawright|last=Seawright|first=Jason|date=September 2016|website=Cambridge Core|language=en|access-date=2019-04-18|doi=10.1017/CBO9781316160831|isbn=9781316160831}}</ref> Advocates of diverse methodological approaches argue that different methodologies are better suited to different subjects of study. Sociologist Herbert Smith and Political Scientists James Mahoney and Gary Goertz have cited the observation of Paul Holland, a statistician and author of the 1986 article “Statistics and Causal Inference,” that statistical inference is most appropriate for assessing the “effects of causes” rather than the “causes of effects.”<ref>{{Cite journal|last=Smith|first=Herbert L.|date=10 February 2014|title=Effects of Causes and Causes of Effects: Some Remarks from the Sociological Side|journal=Sociological Methods and Research|volume=43|issue=3|pages=406–415|doi=10.1177/0049124114521149|pmid=25477697|pmc=4251584}}</ref><ref>{{Cite journal|last=Goertz|first=Gary|last2=Mahoney|first2=James|date=2006|title=A Tale of Two Cultures: Contrasting Quantitative and Qualitative Research|journal=Political Analysis|language=en|volume=14|issue=3|pages=227–249|doi=10.1093/pan/mpj017|issn=1047-1987}}</ref> Qualitative methodologists have argued that formalized models of causation, including process tracing and fuzzy set theory, provide opportunities to infer causation through the identification of critical factors within case studies or through a process of comparison among several case studies.<ref name=":0" /> These methodologies are also valuable for subjects in which a limited number of potential observations or the presence of confounding variables would limit the applicability of statistical inference.{{Citation needed|date=May 2019}}

虽然在潜在结果框架中大部分重点仍然放在统计推论上，但社会科学方法学家已经开发出新的定性和定量方法来进行因果推断，有时被称为'''混合方法mixed methods'''。多种不同方法的支持者认为它更适合'''不同学科的研究different subjects of study'''。
--[[用户:嘉树|嘉树]]（[[用户讨论:嘉树|讨论]]）学科还是对象？
社会学家 Herbert Smith 和政治学家 James Mahoney 、 Gary Goertz 引用了统计学家 Paul Holland 的观察结果，Paul Holland在1986年发表了一篇名为《'''统计学和因果推断Statistics and Causal Inference'''》的文章，认为推论统计学最适合于评估“结果的原因”而不是“结果的原因”。定性方法学家认为，形式化的因果关系模型，包括'''过程追踪process tracing'''和'''模糊集理论fuzzy set theory'''，通过在某个案例研究内识别关键因素或在几个案例研究之间比较的过程提供了推断因果关系的机会。这些方法对于那些可能的观察数量有限或存在混淆变量从而限制统计推论适用性的课题也是有价值的。
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“虽然在潜在结果框架中大部分重点仍然放在统计推论上”一句中“虽然”改为“尽管”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“但社会科学方法学家已经开发出新的定性和定量方法来进行因果推断”一句中“新的定性和定量方法来进行因果推断”改为“使用定性和定量方法进行因果推断的新工具”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“多种不同方法的支持者认为它更适合”一句中“多种不同方法”改为“各种方法论”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“不同学科的研究”一句中的“学科”改为“对象”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“认为推论统计学最适合于评估“结果的原因”而不是“结果的原因””一句中“结果的原因”改为“因果效应”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“通过在某个案例研究内识别关键因素或在几个案例研究之间比较的过程提供了推断因果关系的机会。”一句中“几个”改为“多个”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“这些方法对于那些可能的观察数量有限或存在混淆变量从而限制统计推论适用性的课题也是有价值的。”一句中“那些可能的观察数量有限”改为“那些潜在观察结果的数量受限”

== See also ==

参见
* [[Causal analysis]] 因果分析

* [[Granger causality]] 格兰杰因果分析

* [[Multivariate statistics]] 多元统计

* [[Partial least squares regression]] 偏最小二乘回归

* [[Pathogenesis]] 发病学

* [[Pathology]] 病理学

* [[Regression analysis]] 回归分析

* [[Transfer entropy]] 传递熵

== References ==

参考资料
{{Reflist}}

==Bibliography==

参考书目
* {{cite book |ref=what_if |last1=Hernán |first1=MA |author-link1=Miguel Hernán |last2=Robins |first2=JM |author-link2=James Robins |title=Causal Inference: What If |location=Barnsley |publisher=Boca Raton: Chapman & Hall/CRC |date=2020-01-21|url=https://www.hsph.harvard.edu/miguel-hernan/causal-inference-book/}}

==External links==

外部链接
{{Commons category}}

*[http://clopinet.com/isabelle/Projects/NIPS2013/ NIPS 2013 Workshop on Causality]

*[http://webdav.tuebingen.mpg.de/causality/ Causal inference at the Max-Planck-Institute for Intelligent Systems Tübingen]

{{Portal bar|Science}}

{{Use dmy dates|date=October 2019}}

== 编者推荐 ==
===集智课程推荐===
[https://campus.swarma.org/course/1078 社交网络中的因果推断] 本课程中，将简要介绍一些基本的因果推断策略，并聚焦社会网络分析中的因果推断问题，涉及社会网络实验设计、固定样本、工具变量和敏感度分析等。

===书籍推荐===
[https://book.douban.com/subject/33438811/ 为什么:关于因果关系的新科学] 在本书中，人工智能领域的权威专家Judea Pearl及其同事领导的因果关系革命突破多年的迷雾，厘清了知识的本质，确立了因果关系研究在科学探索中的核心地位。

[[Category:Causal inference| ]]

[[Category:Graphical models]]

类别: 图形模型
[[Category:Regression analysis]]

类别: 回归分析
[[Category:Inductive reasoning]]

类别: 归纳推理
[[Category:Philosophy of statistics]]

分类: 统计哲学
<noinclude>

This page was moved from [[wikipedia:en:Causal inference]]. Its edit history can be viewed at [[因果推断/edithistory]]</noinclude><noinclude>

This page was moved from [[mywiki:zh-cn:因果推断]]. Its edit history can be viewed at [[因果推断/edithistory]]</noinclude>

因果推断

2020-09-18T19:22:25Z

Zc1234567：

{{short description|Branch of statistics concerned with inferring causal relationships between variables}}

{{Expert needed|date=October 2019}}

'''Causal inference''' is the process of drawing a conclusion about a [[causal]] connection based on the conditions of the occurrence of an effect. The main difference between causal inference and inference of [[association (statistics)|association]] is that the former analyzes the response of the effect variable when the cause is changed.<ref name=Pearl_Journal>{{cite journal|last=Pearl|first=Judea|title=Causal inference in statistics: An overview|journal=Statistics Surveys|date=1 January 2009|volume=3|issue=|pages=96–146|doi=10.1214/09-SS057|url=http://ftp.cs.ucla.edu/pub/stat_ser/r350.pdf}}</ref><ref name=Morgan_book>{{cite book|last=Morgan|first=Stephen|author2=Winship, Chris|title=Counterfactuals and Causal inference|publisher=Cambridge University Press|year=2007|isbn=978-0-521-67193-4}}</ref> The science of why things occur is called [[etiology]]. Causal inference is an example of [[causal reasoning]].

'''因果推断Causal inference'''是根据某一效应发生的条件得出关于因果关系的结论的过程。因果推断与'''关联推理inference of association'''的主要区别在于前者分析在原因变化时结果变量的反应。研究事情为什么发生的科学叫做'''病因学etiology'''。因果推断是'''因果推理causal reasoning'''的一个例子。

--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“是根据某一效应发生的条件得出关于因果关系的结论的过程。”一句中的“根据”改为“基于”，“效应”改为“事件”，“因果关系的结论”改为“因果联系结论”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“的主要区别在于前者分析在原因变化时结果变量的反应。”一句中“在原因变化时”改为“了当原因改变时”,“反应”改为“响应”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“研究事情为什么发生的科学叫做”一句改为“研究事件因何而起的科学被称为”

==Definition定义==

Inferring the [[cause]] of something has been described as:

'''对某事原因的推断过程已经被描述为是:Inferring the [[cause]] of something has been described as:'''

--[[用户:嘉树|嘉树]]（[[用户讨论:嘉树|讨论]]） inferring是ing形式，因此译为“推断的过程”，存疑
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“对某事原因的推断过程已经被描述为是：”一句改为“推断某事原因的过程被描述为：”

*"...reason[ing] to the conclusion that something is, or is likely to be, the cause of something else".<ref name=EB>{{cite web|title=causal inference|url=http://www.britannica.com/EBchecked/topic/1442615/causal-inference|publisher=Encyclopædia Britannica, Inc.|accessdate=24 August 2014}}</ref>

*“推理得出某事是（或可能是）其他事情的原因这一结论的过程。”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“推理得出某事是（或可能是）其他事情的原因这一结论的过程。”一句改为“某事是（或可能是）其他事情的原因这一结论。”
*"Identification of the cause or causes of a phenomenon, by establishing covariation of cause and effect, a time-order relationship with the cause preceding the effect, and the elimination of plausible alternative causes."<ref name=psy>{{cite book|author1=John Shaughnessy|author2=Eugene Zechmeister|author3=Jeanne Zechmeister|title=Research Methods in Psychology|date=2000|publisher=McGraw-Hill Humanities/Social Sciences/Languages|isbn=978-0077825362|pages=Chapter 1 : Introduction|url=http://www.mhhe.com/socscience/psychology/shaugh/ch01_concepts.html|accessdate=24 August 2014|archive-url=https://web.archive.org/web/20141015135541/http://www.mhhe.com/socscience/psychology/shaugh/ch01_concepts.html|archive-date=15 October 2014|url-status=dead}}</ref>

*“通过建立因果的共变关系、建立原因先于结果的时间顺序关系，以及消除其他可能的替代原因的过程，从而对现象的一个或多个原因进行确定的过程。”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“通过建立因果的共变关系、建立原因先于结果的时间顺序关系，以及消除其他可能的替代原因的过程，从而对现象的一个或多个原因进行确定的过程。”一句改为“通过建立因果的共变模型，前因后果的时间顺序联系，以及消除其他可能的替代原因，从而对现象的一个或多个原因进行确认。”
==Methods 方法==

Epidemiological studies employ different [[epidemiological method]]s of collecting and measuring evidence of risk factors and effect and different ways of measuring association between the two. A [[hypothesis]] is formulated, and then [[Statistical hypothesis testing|tested with statistical methods]]. It is [[statistical inference]] that helps decide if data are due to chance, also called [[random variation]], or indeed correlated and if so how strongly. However, [[correlation does not imply causation]], so further methods must be used to infer causation.{{Citation needed|date=May 2019}}

'''流行病学epidemiological'''收集和衡量危险因素和结果，以及衡量危险因素和结果之间关系的方法与其他学科不同。一个假设提出来以后用'''统计学假设检验Statistical hypothesis testing'''。这种'''统计学推断statistical inference '''有助于判断数据是由偶然性引起的，也就是'''随机变异random variation'''，还是确实存在相关性，以及相关性有多强。然而，相关不意味着因果，因此必须进一步使用其他方法来推断因果关系。
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“收集和衡量危险因素和结果，以及衡量危险因素和结果之间关系的方法与其他学科不同。一个假设提出来以后用”一句改为“运用不同的流行病模型来收集和衡量危险因素和结果，以及判定两者之间的联系”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“一个假设提出来以后”一句改为“一个假说被提出来后”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“是由偶然性引起的，也就是”一句改为“是否由偶然性引起，也被称为”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“还是确实存在相关性，以及相关性有多强”一句改为“还是确实相关以及相关性的强弱”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“因此必须进一步使用其他方法来推断因果关系”一句改为“必须使用其他方法来推断其因果关系”
Common frameworks for causal inference are [[structural equation modeling]] and the [[Rubin causal model]].{{citation needed|date=August 2014}}

因果推断的常见框架有'''结构方程模型structural equation modeling'''和'''Rubin因果模型 Rubin causal model'''。

--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“因果推断的常见框架”一句改为“常见的因果推断框架有”
==In epidemiology 在流行病学中==

[[Epidemiology]] studies patterns of health and disease in defined populations of [[living beings]] in order to [[infer]] causes and effects. An association between an [[Exposure (environmental hazard)|exposure]] to a putative [[risk factor]] and a disease may be suggestive of, but is not equivalent to causality because [[correlation does not imply causation]]. Historically, [[Koch's postulates]] have been used since the 19th century to decide if a microorganism was the cause of a disease. In the 20th century the [[Bradford Hill criteria]], described in 1965<ref name="bh65">{{cite journal |last=Hill |first=Austin Bradford |year=1965 |title=The Environment and Disease: Association or Causation? |journal=[[Proceedings of the Royal Society of Medicine]] |volume=58 |pages=295–300 |url=http://www.edwardtufte.com/tufte/hill |pmid=14283879 |pmc=1898525 |issue=5 |doi=10.1177/003591576505800503}}</ref> have been used to assess causality of variables outside microbiology, although even these criteria are not exclusive ways to determine causality.

'''流行病学Epidemiology'''研究特定生物群体的健康和疾病'''模式patterns'''，以推断原因和结果。'''暴露exposure '''于一般认为的'''危险因素risk factor'''和疾病之间的联系可能被提出，但不等同于确认因果关系，因为相关不意味着因果。从历史上看，'''科赫法则 Koch's postulates'''从19世纪开始就被用来判断一种微生物是否是一种疾病的原因。在20世纪，'''布拉德福德·希尔准则Bradford Hill criteria'''（参见Bradford Hill 1965年的文章<ref name="bh65"></ref>中）已经被用来评估微生物学之外的变量的因果关系，尽管即使是这些标准也不是确定因果关系的唯一方法。

--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“的联系可能被提出，但不等同于确认因果关系”一句改为，“可能存在关联，但不等于确定因果关系”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“从19世纪开始”将此短语提至“科赫法则”之前。
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“疾病的原因”一词改为“疾病病因”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“尽管即使是这些标准也不是确定因果关系的唯一方法”一句中去掉“即使”

In [[molecular epidemiology]] the phenomena studied are on a [[molecular biology]] level, including genetics, where [[biomarkers]] are evidence of cause or effects.

'''分子流行病学molecular epidemiology'''中研究的现象是在'''分子生物学'''水平上的，也涵盖了遗传学。而遗传学中的'''生物标志物biomarkers'''就是原因或结果的证据。

--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“分子生物学”一词改成“生物分子”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“水平上的，也涵盖了遗传学。而遗传学中的”一句改为“水平上也涵盖了遗传学，而其中”

A recent trend{{when|date=August 2014}} is to identify [[evidence]] for influence of the exposure on [[molecular pathology]] within diseased [[Tissue (biology)|tissue]] or cells, in the emerging interdisciplinary field of [[molecular pathological epidemiology]] (MPE).{{third-party-inline|date=August 2014}} Linking the exposure to molecular pathologic signatures of the disease can help to assess causality. {{third-party-inline|date=August 2014}} Considering the inherent nature of [[heterogeneity]] of a given disease, the unique disease principle, disease phenotyping and subtyping are trends in biomedical and [[public health]] sciences, exemplified as [[personalized medicine]] and [[precision medicine]].{{third-party-inline|date=August 2014}}

在新兴的'''分子病理流行病学molecular pathological epidemiology (MPE)'''交叉学科领域，最近的一个趋势（截至2014年）是确定在病变组织或细胞内，'''暴露exposure '''在'''分子病理学molecular pathology'''上的影响。将暴露与疾病的分子病理特征联系起来可以帮助因果关系的评估。鉴于给定疾病的'''异质性'''的固有特征、独特的疾病原理等，疾病'''表现型phenotyping'''和'''亚型subtyping '''现在是生物医学和'''公共卫生科学public health'''的趋势，例证包括'''个体化医学personalized medicine'''和'''精准医学precision medicine'''等。

--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“暴露”改为“暴露迹象”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“上的影响”改为“影响的证据”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“将暴露”改为“将暴露迹象”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“因果关系的评估”改为“评估因果关系”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“给定疾病的”改为“特定疾病”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“独特的疾病原理等”改为“罕见的病理”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“现在是生物医学和”改为“是生物医学和”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“个体化医学”改为“私人医疗”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“精准医学”改为“精密医学”
==In computer science在计算机科学领域==

Determination of cause and effect from joint observational data for two time-independent variables, say X and Y, has been tackled using asymmetry between evidence for some model in the directions, X → Y and Y → X. The primary approaches are based on [[Algorithmic information theory]] models and noise models.{{Citation needed|date=May 2019}}

确定两个时间独立变量：X 和 Y 的联合观测数据因果关系的问题已经被解决了，方法是利用 X → Y 和 Y → X 方向上某些模型的证据不对称性。主要的方法基于'''算法信息理论Algorithmic information theory'''模型和'''噪声模型noise models'''。

--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“确定两个时间独立变量：X 和 Y 的联合观测数据因果关系的问题已经被解决了，方法是利用 X → Y 和 Y → X 方向上某些模型的证据不对称性。”改为“由两个时间自变量，例如X,Y；联合观测数据来确定因果关系。已经被使用一些模型方向上证据的不对称性给解决了，例如：X → Y 和 Y → X 。”

===Algorithmic information models算法信息模型===

Compare two programs, both of which output both X and Y.

比较两个同时输出 X 和 Y 的程序。
* Store Y and a compressed form of X in terms of uncompressed Y.

* Store X and a compressed form of Y in terms of uncompressed X.

* 用未压缩的 X 来存储 X 和压缩形式的 Y 。

--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“用未压缩的 X 来存储 X 和压缩形式的 Y ”改为“根据未压缩的Y存储Y和X的压缩型，根据未压缩的X存储X和Y的压缩型”

The shortest such program implies the uncompressed stored variable more-likely causes the computed variable.<ref>Kailash Budhathoki and Jilles Vreeken "[http://eda.mmci.uni-saarland.de/pubs/2016/origo-budhathoki,vreeken.pdf Causal Inference by Compression]" 2016 IEEE 16th International Conference on Data Mining (ICDM)</ref><ref>{{Cite journal |doi = 10.1007/s10115-018-1286-7|title = Telling cause from effect by local and global regression|journal = Knowledge and Information Systems|year = 2018|last1 = Marx|first1 = Alexander|last2 = Vreeken|first2 = Jilles|volume=60|issue = 3|pages=1277–1305|doi-access = free}}</ref>

最短的这种程序意味着，更有可能是未压缩的'''存储变量stored variable'''导致了'''计算出的变量computed variable'''。

--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“最短的这种程序意味着”改为“最短的此类程序表明”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“计算出的变量”改为“计算变量”

===Noise models噪音模型===

Incorporate an independent noise term in the model to compare the evidences of the two directions.

在模型中引入一个独立的噪声项，以比较两个方向的证据。

Here are some of the noise models for the hypothesis Y → X with the noise E:

下面是一些支持 Y → X 假设且具有噪声 E 的噪声模型:
* Additive noise:<ref>Hoyer, Patrik O., et al. "[https://papers.nips.cc/paper/3548-nonlinear-causal-discovery-with-additive-noise-models.pdf Nonlinear causal discovery with additive noise models]." NIPS. Vol. 21. 2008.</ref> <math>Y = F(X)+E</math>
* '''加法噪音Additive noise'''

* Linear noise:<ref>{{cite journal | last1 = Shimizu | first1 = Shohei | display-authors = etal | year = 2011 | title = DirectLiNGAM: A direct method for learning a linear non-Gaussian structural equation model | url = http://www.jmlr.org/papers/volume12/shimizu11a/shimizu11a.pdf | journal = The Journal of Machine Learning Research | volume = 12 | issue = | pages = 1225–1248 }}</ref> <math>Y = pX + qE</math>
* '''线性噪音Linear noise'''

* Post-non-linear:<ref>Zhang, Kun, and Aapo Hyvärinen. "[https://arxiv.org/pdf/1205.2599 On the identifiability of the post-nonlinear causal model]." Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence. AUAI Press, 2009.</ref> <math>Y = G(F(X)+E)</math>
* '''后非线性Post-non-linear（噪音）'''

* Heteroskedastic noise: <math>Y = F(X)+E.G(X)</math>
* '''异方差噪音Heteroskedastic noise'''

* Functional noise:<ref name="Mooij">Mooij, Joris M., et al. "[http://papers.nips.cc/paper/4173-probabilistic-latent-variable-models-for-distinguishing-between-cause-and-effect.pdf Probabilistic latent variable models for distinguishing between cause and effect]." NIPS. 2010.</ref> <math>Y = F(X,E)</math>
* '''功能性噪音Functional noise'''

The common assumption in these models are:

这些模型的共同假设是:
* There are no other causes of Y.
* Y 没有其他原因。

* X and E have no common causes.
* X 和 E 没有共同的原因。

* Distribution of cause is independent from causal mechanisms.
* 原因的分布独立于因果机制。

On an intuitive level, the idea is that the factorization of the joint distribution P(Cause, Effect) into P(Cause)*P(Effect | Cause) typically yields models of lower total complexity than the factorization into P(Effect)*P(Cause | Effect). Although the notion of “complexity” is intuitively appealing, it is not obvious how it should be precisely defined.<ref name="Mooij"/> A different family of methods attempt to discover causal "footprints" from large amounts of labeled data, and allow the prediction of more flexible causal relations.<ref>Lopez-Paz, David, et al. "[http://www.jmlr.org/proceedings/papers/v37/lopez-paz15.pdf Towards a learning theory of cause-effect inference]" ICML. 2015</ref>

在直观的层面上，这个想法是联合分布P(Cause, Effect) 到 P(Cause)*P(Effect | Cause)的因式分解通常产生的模型的总'''复杂性complexity '''低于到P(Effect)*P(Cause | Effect)的因式分解。尽管“复杂性”的概念在直觉上很吸引人，但是对于如何定义它却并不显而易见。另一种不同类族的方法尝试从大量标签过的数据中发现因果的“足迹”，并且允许预测更灵活的因果关系。
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“这个想法是联合分布P(Cause, Effect) 到 P(Cause)*P(Effect | Cause)的因式分解通常产生的模型的总”改为“联合分布P(起因,结果)到P(起因)*P(结果|起因)拆分的主意通常产生模型的总”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“低于到P(Effect)*P(Cause | Effect)的因式分解”改为“低于将P(起因,结果)到P(结果)*P(起因|结果)的拆分”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“但是对于如何定义”改为“但对于应该如何精确定义”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“标签过”改为“被标记”

== In statistics and economics 在统计学和经济学领域==

{{Main|Causality#Statistics and economics}}

--[[用户:嘉树|嘉树]]（[[用户讨论:嘉树|讨论]]）本段似有错漏，英文词条和本段内容有一些不同。因此，（1）先写本段的翻译，（2）再写英文词条中有不同的地方，（3）最后整合一下。【】括起来的是在两个版本中需要照应和修改的部分。

In [[statistics]] and [[economics]], causality is often tested via [[regression analysis]]. Several methods can be used to distinguish actual causality from spurious correlations. First, economists constructing regression models establish the direction of causal relation based on economic theory (theory-driven econometrics). For example, if one studies the dependency between rainfall and the future price of a commodity, then theory (broadly construed) indicates that rainfall can influence prices, but futures prices cannot make changes to the amount of rain<ref>{{Cite book|last=Simon|first=Herbert|title=Models of Discovery|publisher=Springer|year=1977|location=Dordrecht|page=52}}</ref> . Second, the [[instrumental variables]] (IV) technique may be employed to remove any reverse causation by introducing a role for other variables (instruments) that are known to be unaffected by the dependent variable. Third, economists consider time precedence to choose appropriate model specification. Given that partial correlations are symmetrical, one cannot determine the direction of causal relation based on correlations only. Based on the notion of probabilistic view on causality, economists assume that causes must be prior in time than their effects. This leads to using the variables representing phenomena happening earlier as independent variables and developing econometric tests for causality (e.g., Granger-causality tests) applicable in time series analysis<ref>{{Cite book|last=Maziarz|first=Mariusz|title=The Philosophy of Causality in Economics: Causal Inferences and Policy Proposals|publisher=Routledge|year=2020|location=New York}}</ref>. Fifth, other regressors are included to ensure that [[confounding variable]]s are not causing a regressor to appear to be significant spuriously but, in the areas suffering from the problem of multicollinearity such as macroeconomics, it is in principle impossible to include all confounding factors and therefore econometric models are susceptible to the common-cause fallacy.<ref>{{Cite journal|last=Henschen|first=Tobias|date=2018|title=The in-principle inconclusiveness of causal evidence in macroeconomics|journal=European Journal for Philosophy of Science|volume=8|pages=709–733}}</ref>. Recently, the movement of design-based econometrics has popularized using natural experiments and quasi-experimental research designs to address the problem of spurious correlations.<ref>{{Cite book|last=Angrist Joshua & Pischke Jörn-Steffen|title=Mostly Harmless Econometrics: An Empiricist's Companion|publisher=Princeton University Press|year=2008|location=Princeton}}</ref>

在统计学和经济学中，因果关系通常通过回归分析来检验。有几种方法可以用来区分真实的因果关系和虚假的相关性。第一，经济学家根据经济理论('''理论驱动theory-driven'''的计量经济学)构建回归模型，从而确定因果关系的方向。
例如，如果研究降雨与未来商品价格之间的依赖关系，那么一个广义上建构的理论表明，降雨可以影响价格，但未来价格不能改变降雨量。<ref>{{Cite book|last=Simon|first=Herbert|title=Models of Discovery|publisher=Springer|year=1977|location=Dordrecht|page=52}}</ref> . 第二，'''工具变量instrumental variables(IV)'''技术可以通过引入其他已知不受因变量的影响的工具变量来消除任何反向因果关系。【第三，经济学家会考虑时间优先级来选择合适的具体模型。由于'''偏相关partial correlations'''是对称的，人们不能在相关的基础上确定因果关系的方向。经济学家基于因果关系的'''概率观点probabilistic view'''假设，原因必须在时间上优先于其结果。这导致经济学家使用较早发生的现象作为自变量，并开发适用于时间序列分析的因果关系检验计量经济方法（例如，'''格兰杰因果检验'''）<ref>{{Cite book|last=Maziarz|first=Mariusz|title=The Philosophy of Causality in Economics: Causal Inferences and Policy Proposals|publisher=Routledge|year=2020|location=New York}}</ref>。第五，有些做法包括了其他回归项，从而确保'''混淆变量confounding variables'''不会导致某个回归因素显得明显虚假，但遭受'''多重共线性multicollinearity'''问题困扰的领域，如宏观经济学，原则上不可能包括所有混淆因素，因此计量经济模型容易出现'''共因谬误common-cause fallacy'''<ref>{{Cite journal|last=Henschen|first=Tobias|date=2018|title=The in-principle inconclusiveness of causal evidence in macroeconomics|journal=European Journal for Philosophy of Science|volume=8|pages=709–733}}</ref>。近年来，'''以研究设计为基础的计量经济学design-based econometrics'''运动已经推广使用自然实验和准实验研究设计来解决'''虚假相关spurious correlations'''的问题<ref>{{Cite book|last=Angrist Joshua & Pischke Jörn-Steffen|title=Mostly Harmless Econometrics: An Empiricist's Companion|publisher=Princeton University Press|year=2008|location=Princeton}}</ref>。】

--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】有几种方法可以用来区分真实的因果关系和虚假的相关性。一句中的“区分”改为“鉴别”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】从而确定因果关系的方向，一句中“确定”改为“建立”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】如果研究降雨与未来商品价格之间的依赖关系，一句中“未来商品价格”改为“一种商品的未来价格
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】那么一个广义上建构的理论表明，一句中“一个”去掉。
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】技术可以通过引入其他已知不受因变量的影响的工具变量来消除任何反向因果关系。一句中“工具变量”改为“变量（工具）”；“反向因果”改为“逆因果”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】经济学家会考虑时间优先级来选择合适的具体模型。一句中“会”改为“会通过”；“合适的具体模型”改为“适当的模型规范”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“人们不能在相关的基础上确定因果关系的方向”一句改为“不能仅仅根据一方面的相关性来确定因果关系的方向”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“经济学家基于因果关系的”一句改为“基于因果关系的”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“假设，原因必须在时间上优先于其结果”一句改为“经济学家假设，在时间上原因必须先于其结果”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“并开发适用于时间序列分析的因果关系检验计量经济方法”一句中的“检验计量经济方法”改为“计量经济学的检验方法”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“不会导致某个回归因素显得明显虚假”一句中的“明显虚假”改为“过于虚假”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“但遭受”中的“但”改为“但在”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“以研究设计为基础的计量经济学”一句中“研究”去掉。
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“运动已经推广使用自然实验和准实验研究设计来解决”一句中“运动已经推广”改为“活动已经推广至”

--[[用户:嘉树|嘉树]]（[[用户讨论:嘉树|讨论]]）英文词条的第三和第四：

Third, the principle that effects cannot precede causes can be invoked, by including on the right side of the regression only variables that precede in time the dependent variable.
Fourth, other regressors are included to ensure that confounding variables are not causing a regressor to spuriously appear to be significant. Correlation by coincidence, as opposed to correlation reflecting actual dependence of the underlying process, can be ruled out by using large samples and by performing cross validation to check that correlations are maintained on data that were not used in the regression.

【第三，通过在回归的右侧只包括时间上在因变量之前的变量，就可以使用结果不能优先于原因的原则。
第四，有些方法包括了其他回归因素，以确保'''混淆变量confounding variables'''不会导致一个回归项虚假地呈现显著。通过使用大样本和交叉验证检查在回归中未使用的数据上是否保持了相关性，可以排除巧合的，而不是反映实际依赖内在过程的相关性。】

--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“通过在回归的右侧只包括时间上在因变量之前的变量”改为“在正向回归中只包含在时间上早于因变量的变量”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“就可以使用结果不能优先于原因的原则”改为“就可以引用结果不能先于原因的原则”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“有些方法包括了其他回归因素，以确保”改为“有些方法包括了其他回归因素以确保”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“不会导致一个回归项虚假地呈现显著”改为“不会导致回归项虚假地呈现这种现象十分重要”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“通过使用大样本和交叉验证检查在回归中未使用的数据上是否保持了相关性，可以排除巧合的，而不是反映实际依赖内在过程的相关性。”一句改为“通过使用大规模样本和交叉验证来检查在回归中未使用的数据是否保持了相关，这样可以排除因巧合的相关性，而不是反映实际依赖内在过程的相关性。”
--[[用户:嘉树|嘉树]]（[[用户讨论:嘉树|讨论]]）整合后的翻译：

在统计学和经济学中，因果关系通常通过回归分析来检验。有几种方法可以用来区分真实的因果关系和虚假的相关性。第一，经济学家根据经济理论('''理论驱动theory-driven'''的计量经济学)构建回归模型，从而确定因果关系的方向。例如，如果研究降雨与未来商品价格之间的依赖关系，那么一个广义上建构的理论表明，降雨可以影响价格，但未来价格不能改变降雨量。<ref>{{Cite book|last=Simon|first=Herbert|title=Models of Discovery|publisher=Springer|year=1977|location=Dordrecht|page=52}}</ref> . 第二，'''工具变量instrumental variables(IV)'''技术可以通过引入其他已知不受因变量的影响的工具变量来消除任何反向因果关系。第三，通过在回归的右侧只包括时间上在因变量之前的变量，就可以使用结果不能优先于原因的原则。由于'''偏相关partial correlations'''是对称的，人们不能在相关的基础上确定因果关系的方向。经济学家基于因果关系的'''概率观点probabilistic view'''假设，原因必须在时间上优先于其结果。这导致经济学家使用较早发生的现象作为自变量，并开发适用于时间序列分析的因果关系检验计量经济方法（例如，'''格兰杰因果检验'''）<ref>{{Cite book|last=Maziarz|first=Mariusz|title=The Philosophy of Causality in Economics: Causal Inferences and Policy Proposals|publisher=Routledge|year=2020|location=New York}}</ref>。第四，有些方法包括了其他回归因素，以确保'''混淆变量confounding variables'''不会导致一个回归项虚假地呈现显著。通过使用大样本和交叉验证检查在回归中未使用的数据上是否保持了相关性，可以排除巧合的，而不是反映实际依赖内在过程的相关性。但遭受'''多重共线性multicollinearity'''问题困扰的领域，如宏观经济学，原则上不可能包括所有混淆因素，因此计量经济模型容易出现'''共因谬误common-cause fallacy'''<ref>{{Cite journal|last=Henschen|first=Tobias|date=2018|title=The in-principle inconclusiveness of causal evidence in macroeconomics|journal=European Journal for Philosophy of Science|volume=8|pages=709–733}}</ref>。近年来，'''以研究设计为基础的计量经济学design-based econometrics'''运动已经推广使用自然实验和准实验研究设计来解决'''虚假相关spurious correlations'''的问题<ref>{{Cite book|last=Angrist Joshua & Pischke Jörn-Steffen|title=Mostly Harmless Econometrics: An Empiricist's Companion|publisher=Princeton University Press|year=2008|location=Princeton}}</ref>。

== In social science 在社会科学领域==

The social sciences have moved increasingly toward a quantitative framework for assessing causality. Much of this has been described as a means of providing greater rigor to social science methodology. Political science was significantly influenced by the publication of [[Designing Social Inquiry]], by Gary King, Robert Keohane, and Sidney Verba, in 1994. King, Keohane, and Verba (often abbreviated as KKV) recommended that researchers applying both quantitative and qualitative methods adopt the language of statistical inference to be clearer about their subjects of interest and units of analysis.<ref>{{Cite book|title=Designing social inquiry : scientific inference in qualitative research|first=Gary|last=King|date=2012|publisher=Princeton Univ. Press|isbn=978-0691034713|oclc=754613241}}</ref><ref name=":0">{{Cite journal|last=Mahoney|first=James|date=January 2010|title=After KKV|journal=World Politics|volume=62|issue=1|pages=120–147|jstor=40646193|doi=10.1017/S0043887109990220}}</ref> Proponents of quantitative methods have also increasingly adopted the [[Rubin causal model|potential outcomes framework]], developed by [[Donald Rubin]], as a standard for inferring causality.{{Citation needed|date=May 2019}}

社会科学越来越倾向评估因果关系的定量框架。框架中的很大一部分已经被描述为一种提供更严格的'''社会科学方法social science methodology'''的方式。1994年，'''加里·金Gary King'''、'''罗伯特 · 基奥汉Robert Keohane'''和'''西德尼 · 维尔巴Sidney Verba'''合著的《'''设计社会学问卷Designing Social Inquiry'''》对政治科学产生了重大影响。'''金、基奥汉，和维尔巴（通常缩写为 KKV）建议研究人员同时采用定量和定性的方法，采用统计推论的语言来更清楚地说明他们感兴趣的主题和分析的单位。King, Keohane, and Verba (often abbreviated as KKV) recommended that researchers applying both quantitative and qualitative methods adopt the language of statistical inference to be clearer about their subjects of interest and units of analysis.'''<ref>{{Cite book|title=Designing social inquiry : scientific inference in qualitative research|first=Gary|last=King|date=2012|publisher=Princeton Univ. Press|isbn=978-0691034713|oclc=754613241}}</ref><ref name=":0">{{Cite journal|last=Mahoney|first=James|date=January 2010|title=After KKV|journal=World Politics|volume=62|issue=1|pages=120–147|jstor=40646193|doi=10.1017/S0043887109990220}}</ref>定量方法的支持者也越来越多地采用'''唐纳德 · 鲁宾Donald Rubin'''开发的'''潜在结果框架potential outcomes framework'''作为推断因果关系的标准。
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“社会科学越来越倾向评估因果关系的定量框架”一句改为“社会科学越来越倾向用定量框架来评估因果关系”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“的方式”改为“的手段”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“建议研究人员同时采用定量和定性的方法，采用统计推论的语言来更清楚地说明他们感兴趣的主题和分析的单位。”改为“建议同时采用定量和定性方法的研究人员采用统计推断的语言，以便更清楚地了解他们感兴趣的主题和分析单位。”

Debates over the appropriate application of quantitative methods to infer causality resulted in increased attention to the reproducibility of studies. Critics of widely-practiced methodologies argued that researchers have engaged in [[Data dredging|P hacking]] to publish articles on the basis of spurious correlations.<ref>{{Cite news|url=https://www.nytimes.com/2017/10/18/magazine/when-the-revolution-came-for-amy-cuddy.html|title=When the Revolution Came for Amy Cuddy|last=Dominus|first=Susan|date=18 October 2017|work=The New York Times|access-date=2019-03-02|language=en-US|issn=0362-4331}}</ref> To prevent this, some have advocated that researchers preregister their research designs prior to conducting to their studies so that they do not inadvertently overemphasize a non-reproducible finding that was not the initial subject of inquiry but was found to be statistically significant during data analysis.<ref>{{Cite web|url=https://www.americanscientist.org/article/the-statistical-crisis-in-science|title=The Statistical Crisis in Science|date=6 February 2017|website=American Scientist|language=en|access-date=2019-04-18}}</ref> Internal debates about methodology and reproducibility within the social sciences have at times been acrimonious.{{Citation needed|date=May 2019}}

合适地应用定量方法来推断因果关系的相关争论导致了对研究'''可重复性reproducibility'''的更多关注。对广泛被使用的方法持批评态度的人认为，研究人员利用'''数据挖掘Data dredging'''或'''p-hacking'''技术以在虚假相关的基础上发表文章<ref>{{Cite news|url=https://www.nytimes.com/2017/10/18/magazine/when-the-revolution-came-for-amy-cuddy.html|title=When the Revolution Came for Amy Cuddy|last=Dominus|first=Susan|date=18 October 2017|work=The New York Times|access-date=2019-03-02|language=en-US|issn=0362-4331}}</ref>。为了避免这种情况的发生，一些人主张研究人员在进行研究之前'''预注册preregister'''他们的研究设计，这样他们就不会无意中过分强调一项不可复制的发现，这项发现并非最初的调查对象，但在数据分析中被发现具有统计意义<ref>{{Cite web|url=https://www.americanscientist.org/article/the-statistical-crisis-in-science|title=The Statistical Crisis in Science|date=6 February 2017|website=American Scientist|language=en|access-date=2019-04-18}}</ref>。社会科学内部关于方法论和可重复性的争论有时是尖锐的{{Citation needed|date=May 2019}}。
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】

While much of the emphasis remains on statistical inference in the potential outcomes framework, social science methodologists have developed new tools to conduct causal inference with both qualitative and quantitative methods, sometimes called a “mixed methods” approach.<ref>{{Cite book|url=https://books.google.com/books/about/Designing_and_Conducting_Mixed_Methods_R.html?id=YcdlPWPJRBcC|title=Designing and Conducting Mixed Methods Research|last=Creswell|first=John W.|last2=Clark|first2=Vicki L. Plano|date=2011|publisher=SAGE Publications|isbn=9781412975179|language=en}}</ref><ref>{{Cite book|url=https://www.cambridge.org/core/books/multimethod-social-science/286C2742878FBCC6225E2F10D6095A0C|title=Multi-Method Social Science by Jason Seawright|last=Seawright|first=Jason|date=September 2016|website=Cambridge Core|language=en|access-date=2019-04-18|doi=10.1017/CBO9781316160831|isbn=9781316160831}}</ref> Advocates of diverse methodological approaches argue that different methodologies are better suited to different subjects of study. Sociologist Herbert Smith and Political Scientists James Mahoney and Gary Goertz have cited the observation of Paul Holland, a statistician and author of the 1986 article “Statistics and Causal Inference,” that statistical inference is most appropriate for assessing the “effects of causes” rather than the “causes of effects.”<ref>{{Cite journal|last=Smith|first=Herbert L.|date=10 February 2014|title=Effects of Causes and Causes of Effects: Some Remarks from the Sociological Side|journal=Sociological Methods and Research|volume=43|issue=3|pages=406–415|doi=10.1177/0049124114521149|pmid=25477697|pmc=4251584}}</ref><ref>{{Cite journal|last=Goertz|first=Gary|last2=Mahoney|first2=James|date=2006|title=A Tale of Two Cultures: Contrasting Quantitative and Qualitative Research|journal=Political Analysis|language=en|volume=14|issue=3|pages=227–249|doi=10.1093/pan/mpj017|issn=1047-1987}}</ref> Qualitative methodologists have argued that formalized models of causation, including process tracing and fuzzy set theory, provide opportunities to infer causation through the identification of critical factors within case studies or through a process of comparison among several case studies.<ref name=":0" /> These methodologies are also valuable for subjects in which a limited number of potential observations or the presence of confounding variables would limit the applicability of statistical inference.{{Citation needed|date=May 2019}}

虽然在潜在结果框架中大部分重点仍然放在统计推论上，但社会科学方法学家已经开发出新的定性和定量方法来进行因果推断，有时被称为'''混合方法mixed methods'''。多种不同方法的支持者认为它更适合'''不同学科的研究different subjects of study'''。
--[[用户:嘉树|嘉树]]（[[用户讨论:嘉树|讨论]]）学科还是对象？
社会学家 Herbert Smith 和政治学家 James Mahoney 、 Gary Goertz 引用了统计学家 Paul Holland 的观察结果，Paul Holland在1986年发表了一篇名为《'''统计学和因果推断Statistics and Causal Inference'''》的文章，认为推论统计学最适合于评估“结果的原因”而不是“结果的原因”。定性方法学家认为，形式化的因果关系模型，包括'''过程追踪process tracing'''和'''模糊集理论fuzzy set theory'''，通过在某个案例研究内识别关键因素或在几个案例研究之间比较的过程提供了推断因果关系的机会。这些方法对于那些可能的观察数量有限或存在混淆变量从而限制统计推论适用性的课题也是有价值的。

== See also ==

参见
* [[Causal analysis]] 因果分析

* [[Granger causality]] 格兰杰因果分析

* [[Multivariate statistics]] 多元统计

* [[Partial least squares regression]] 偏最小二乘回归

* [[Pathogenesis]] 发病学

* [[Pathology]] 病理学

* [[Regression analysis]] 回归分析

* [[Transfer entropy]] 传递熵

== References ==

参考资料
{{Reflist}}

==Bibliography==

参考书目
* {{cite book |ref=what_if |last1=Hernán |first1=MA |author-link1=Miguel Hernán |last2=Robins |first2=JM |author-link2=James Robins |title=Causal Inference: What If |location=Barnsley |publisher=Boca Raton: Chapman & Hall/CRC |date=2020-01-21|url=https://www.hsph.harvard.edu/miguel-hernan/causal-inference-book/}}

==External links==

外部链接
{{Commons category}}

*[http://clopinet.com/isabelle/Projects/NIPS2013/ NIPS 2013 Workshop on Causality]

*[http://webdav.tuebingen.mpg.de/causality/ Causal inference at the Max-Planck-Institute for Intelligent Systems Tübingen]

{{Portal bar|Science}}

{{Use dmy dates|date=October 2019}}

== 编者推荐 ==
===集智课程推荐===
[https://campus.swarma.org/course/1078 社交网络中的因果推断] 本课程中，将简要介绍一些基本的因果推断策略，并聚焦社会网络分析中的因果推断问题，涉及社会网络实验设计、固定样本、工具变量和敏感度分析等。

===书籍推荐===
[https://book.douban.com/subject/33438811/ 为什么:关于因果关系的新科学] 在本书中，人工智能领域的权威专家Judea Pearl及其同事领导的因果关系革命突破多年的迷雾，厘清了知识的本质，确立了因果关系研究在科学探索中的核心地位。

[[Category:Causal inference| ]]

[[Category:Graphical models]]

类别: 图形模型
[[Category:Regression analysis]]

类别: 回归分析
[[Category:Inductive reasoning]]

类别: 归纳推理
[[Category:Philosophy of statistics]]

分类: 统计哲学
<noinclude>

This page was moved from [[wikipedia:en:Causal inference]]. Its edit history can be viewed at [[因果推断/edithistory]]</noinclude><noinclude>

This page was moved from [[mywiki:zh-cn:因果推断]]. Its edit history can be viewed at [[因果推断/edithistory]]</noinclude>

因果推断

2020-09-17T19:50:45Z

Zc1234567：

{{short description|Branch of statistics concerned with inferring causal relationships between variables}}

{{Expert needed|date=October 2019}}

'''Causal inference''' is the process of drawing a conclusion about a [[causal]] connection based on the conditions of the occurrence of an effect. The main difference between causal inference and inference of [[association (statistics)|association]] is that the former analyzes the response of the effect variable when the cause is changed.<ref name=Pearl_Journal>{{cite journal|last=Pearl|first=Judea|title=Causal inference in statistics: An overview|journal=Statistics Surveys|date=1 January 2009|volume=3|issue=|pages=96–146|doi=10.1214/09-SS057|url=http://ftp.cs.ucla.edu/pub/stat_ser/r350.pdf}}</ref><ref name=Morgan_book>{{cite book|last=Morgan|first=Stephen|author2=Winship, Chris|title=Counterfactuals and Causal inference|publisher=Cambridge University Press|year=2007|isbn=978-0-521-67193-4}}</ref> The science of why things occur is called [[etiology]]. Causal inference is an example of [[causal reasoning]].

'''因果推断Causal inference'''是根据某一效应发生的条件得出关于因果关系的结论的过程。因果推断与'''关联推理inference of association'''的主要区别在于前者分析在原因变化时结果变量的反应。研究事情为什么发生的科学叫做'''病因学etiology'''。因果推断是'''因果推理causal reasoning'''的一个例子。

--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“是根据某一效应发生的条件得出关于因果关系的结论的过程。”一句中的“根据”改为“基于”，“效应”改为“事件”，“因果关系的结论”改为“因果联系结论”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“的主要区别在于前者分析在原因变化时结果变量的反应。”一句中“在原因变化时”改为“了当原因改变时”,“反应”改为“响应”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“研究事情为什么发生的科学叫做”一句改为“研究事件因何而起的科学被称为”

==Definition定义==

Inferring the [[cause]] of something has been described as:

'''对某事原因的推断过程已经被描述为是:Inferring the [[cause]] of something has been described as:'''

--[[用户:嘉树|嘉树]]（[[用户讨论:嘉树|讨论]]） inferring是ing形式，因此译为“推断的过程”，存疑
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“对某事原因的推断过程已经被描述为是：”一句改为“推断某事原因的过程被描述为：”

*"...reason[ing] to the conclusion that something is, or is likely to be, the cause of something else".<ref name=EB>{{cite web|title=causal inference|url=http://www.britannica.com/EBchecked/topic/1442615/causal-inference|publisher=Encyclopædia Britannica, Inc.|accessdate=24 August 2014}}</ref>

*“推理得出某事是（或可能是）其他事情的原因这一结论的过程。”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“推理得出某事是（或可能是）其他事情的原因这一结论的过程。”一句改为“某事是（或可能是）其他事情的原因这一结论。”
*"Identification of the cause or causes of a phenomenon, by establishing covariation of cause and effect, a time-order relationship with the cause preceding the effect, and the elimination of plausible alternative causes."<ref name=psy>{{cite book|author1=John Shaughnessy|author2=Eugene Zechmeister|author3=Jeanne Zechmeister|title=Research Methods in Psychology|date=2000|publisher=McGraw-Hill Humanities/Social Sciences/Languages|isbn=978-0077825362|pages=Chapter 1 : Introduction|url=http://www.mhhe.com/socscience/psychology/shaugh/ch01_concepts.html|accessdate=24 August 2014|archive-url=https://web.archive.org/web/20141015135541/http://www.mhhe.com/socscience/psychology/shaugh/ch01_concepts.html|archive-date=15 October 2014|url-status=dead}}</ref>

*“通过建立因果的共变关系、建立原因先于结果的时间顺序关系，以及消除其他可能的替代原因的过程，从而对现象的一个或多个原因进行确定的过程。”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“通过建立因果的共变关系、建立原因先于结果的时间顺序关系，以及消除其他可能的替代原因的过程，从而对现象的一个或多个原因进行确定的过程。”一句改为“通过建立因果的共变模型，前因后果的时间顺序联系，以及消除其他可能的替代原因，从而对现象的一个或多个原因进行确认。”
==Methods 方法==

Epidemiological studies employ different [[epidemiological method]]s of collecting and measuring evidence of risk factors and effect and different ways of measuring association between the two. A [[hypothesis]] is formulated, and then [[Statistical hypothesis testing|tested with statistical methods]]. It is [[statistical inference]] that helps decide if data are due to chance, also called [[random variation]], or indeed correlated and if so how strongly. However, [[correlation does not imply causation]], so further methods must be used to infer causation.{{Citation needed|date=May 2019}}

'''流行病学epidemiological'''收集和衡量危险因素和结果，以及衡量危险因素和结果之间关系的方法与其他学科不同。一个假设提出来以后用'''统计学假设检验Statistical hypothesis testing'''。这种'''统计学推断statistical inference '''有助于判断数据是由偶然性引起的，也就是'''随机变异random variation'''，还是确实存在相关性，以及相关性有多强。然而，相关不意味着因果，因此必须进一步使用其他方法来推断因果关系。
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“收集和衡量危险因素和结果，以及衡量危险因素和结果之间关系的方法与其他学科不同。一个假设提出来以后用”一句改为“运用不同的流行病模型来收集和衡量危险因素和结果，以及判定两者之间的联系”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“一个假设提出来以后”一句改为“一个假说被提出来后”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“是由偶然性引起的，也就是”一句改为“是否由偶然性引起，也被称为”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“还是确实存在相关性，以及相关性有多强”一句改为“还是确实相关以及相关性的强弱”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“因此必须进一步使用其他方法来推断因果关系”一句改为“必须使用其他方法来推断其因果关系”
Common frameworks for causal inference are [[structural equation modeling]] and the [[Rubin causal model]].{{citation needed|date=August 2014}}

因果推断的常见框架有'''结构方程模型structural equation modeling'''和'''Rubin因果模型 Rubin causal model'''。

--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“因果推断的常见框架”一句改为“常见的因果推断框架有”
==In epidemiology 在流行病学中==

[[Epidemiology]] studies patterns of health and disease in defined populations of [[living beings]] in order to [[infer]] causes and effects. An association between an [[Exposure (environmental hazard)|exposure]] to a putative [[risk factor]] and a disease may be suggestive of, but is not equivalent to causality because [[correlation does not imply causation]]. Historically, [[Koch's postulates]] have been used since the 19th century to decide if a microorganism was the cause of a disease. In the 20th century the [[Bradford Hill criteria]], described in 1965<ref name="bh65">{{cite journal |last=Hill |first=Austin Bradford |year=1965 |title=The Environment and Disease: Association or Causation? |journal=[[Proceedings of the Royal Society of Medicine]] |volume=58 |pages=295–300 |url=http://www.edwardtufte.com/tufte/hill |pmid=14283879 |pmc=1898525 |issue=5 |doi=10.1177/003591576505800503}}</ref> have been used to assess causality of variables outside microbiology, although even these criteria are not exclusive ways to determine causality.

'''流行病学Epidemiology'''研究特定生物群体的健康和疾病'''模式patterns'''，以推断原因和结果。'''暴露exposure '''于一般认为的'''危险因素risk factor'''和疾病之间的联系可能被提出，但不等同于确认因果关系，因为相关不意味着因果。从历史上看，'''科赫法则 Koch's postulates'''从19世纪开始就被用来判断一种微生物是否是一种疾病的原因。在20世纪，'''布拉德福德·希尔准则Bradford Hill criteria'''（参见Bradford Hill 1965年的文章<ref name="bh65"></ref>中）已经被用来评估微生物学之外的变量的因果关系，尽管即使是这些标准也不是确定因果关系的唯一方法。

--ZC(讨论) 【审校】“的联系可能被提出，但不等同于确认因果关系”一句改为，“可能存在关联，但不等于确定因果关系”
--ZC(讨论) 【审校】“从19世纪开始”将此短语提至“科赫法则”之前。
--ZC(讨论) 【审校】“疾病的原因”一词改为“疾病病因”
--ZC(讨论) 【审校】“尽管即使是这些标准也不是确定因果关系的唯一方法”一句中去掉“即使”

In [[molecular epidemiology]] the phenomena studied are on a [[molecular biology]] level, including genetics, where [[biomarkers]] are evidence of cause or effects.

'''分子流行病学molecular epidemiology'''中研究的现象是在'''分子生物学'''水平上的，也涵盖了遗传学。而遗传学中的'''生物标志物biomarkers'''就是原因或结果的证据。

--ZC(讨论) 【审校】“分子生物学”一词改成“生物分子”
--ZC(讨论) 【审校】“水平上的，也涵盖了遗传学。而遗传学中的”一句改为“水平上也涵盖了遗传学，而其中”

A recent trend{{when|date=August 2014}} is to identify [[evidence]] for influence of the exposure on [[molecular pathology]] within diseased [[Tissue (biology)|tissue]] or cells, in the emerging interdisciplinary field of [[molecular pathological epidemiology]] (MPE).{{third-party-inline|date=August 2014}} Linking the exposure to molecular pathologic signatures of the disease can help to assess causality. {{third-party-inline|date=August 2014}} Considering the inherent nature of [[heterogeneity]] of a given disease, the unique disease principle, disease phenotyping and subtyping are trends in biomedical and [[public health]] sciences, exemplified as [[personalized medicine]] and [[precision medicine]].{{third-party-inline|date=August 2014}}

在新兴的'''分子病理流行病学molecular pathological epidemiology (MPE)'''交叉学科领域，最近的一个趋势（截至2014年）是确定在病变组织或细胞内，'''暴露exposure '''在'''分子病理学molecular pathology'''上的影响。将暴露与疾病的分子病理特征联系起来可以帮助因果关系的评估。鉴于给定疾病的'''异质性'''的固有特征、独特的疾病原理等，疾病'''表现型phenotyping'''和'''亚型subtyping '''现在是生物医学和'''公共卫生科学public health'''的趋势，例证包括'''个体化医学personalized medicine'''和'''精准医学precision medicine'''等。

--ZC(讨论) 【审校】“暴露”改为“暴露迹象”
--ZC(讨论) 【审校】“上的影响”改为“影响的证据”
--ZC(讨论) 【审校】“将暴露”改为“将暴露迹象”
--ZC(讨论) 【审校】“因果关系的评估”改为“评估因果关系”
--ZC(讨论) 【审校】“给定疾病的”改为“特定疾病”
--ZC(讨论) 【审校】“独特的疾病原理等”改为“罕见的病理”
--ZC(讨论) 【审校】“现在是生物医学和”改为“是生物医学和”
--ZC(讨论) 【审校】“个体化医学”改为“私人医疗”
--ZC(讨论) 【审校】“精准医学”改为“精密医学”
==In computer science在计算机科学领域==

Determination of cause and effect from joint observational data for two time-independent variables, say X and Y, has been tackled using asymmetry between evidence for some model in the directions, X → Y and Y → X. The primary approaches are based on [[Algorithmic information theory]] models and noise models.{{Citation needed|date=May 2019}}

确定两个时间独立变量：X 和 Y 的联合观测数据因果关系的问题已经被解决了，方法是利用 X → Y 和 Y → X 方向上某些模型的证据不对称性。主要的方法基于'''算法信息理论Algorithmic information theory'''模型和'''噪声模型noise models'''。

--ZC(讨论) 【审校】“确定两个时间独立变量：X 和 Y 的联合观测数据因果关系的问题已经被解决了，方法是利用 X → Y 和 Y → X 方向上某些模型的证据不对称性。”改为“由两个时间自变量，例如X,Y；联合观测数据来确定因果关系。已经被使用一些模型方向上证据的不对称性给解决了，例如：X → Y 和 Y → X 。”

===Algorithmic information models算法信息模型===

Compare two programs, both of which output both X and Y.

比较两个同时输出 X 和 Y 的程序。
* Store Y and a compressed form of X in terms of uncompressed Y.

* Store X and a compressed form of Y in terms of uncompressed X.

* 用未压缩的 X 来存储 X 和压缩形式的 Y 。

--ZC(讨论) 【审校】“用未压缩的 X 来存储 X 和压缩形式的 Y ”改为“根据未压缩的Y存储Y和X的压缩型，根据未压缩的X存储X和Y的压缩型”

The shortest such program implies the uncompressed stored variable more-likely causes the computed variable.<ref>Kailash Budhathoki and Jilles Vreeken "[http://eda.mmci.uni-saarland.de/pubs/2016/origo-budhathoki,vreeken.pdf Causal Inference by Compression]" 2016 IEEE 16th International Conference on Data Mining (ICDM)</ref><ref>{{Cite journal |doi = 10.1007/s10115-018-1286-7|title = Telling cause from effect by local and global regression|journal = Knowledge and Information Systems|year = 2018|last1 = Marx|first1 = Alexander|last2 = Vreeken|first2 = Jilles|volume=60|issue = 3|pages=1277–1305|doi-access = free}}</ref>

最短的这种程序意味着，更有可能是未压缩的'''存储变量stored variable'''导致了'''计算出的变量computed variable'''。

--ZC(讨论) 【审校】“最短的这种程序意味着”改为“最短的此类程序表明”
--ZC(讨论) 【审校】“计算出的变量”改为“计算变量”

===Noise models噪音模型===

Incorporate an independent noise term in the model to compare the evidences of the two directions.

在模型中引入一个独立的噪声项，以比较两个方向的证据。

Here are some of the noise models for the hypothesis Y → X with the noise E:

下面是一些支持 Y → X 假设且具有噪声 E 的噪声模型:
* Additive noise:<ref>Hoyer, Patrik O., et al. "[https://papers.nips.cc/paper/3548-nonlinear-causal-discovery-with-additive-noise-models.pdf Nonlinear causal discovery with additive noise models]." NIPS. Vol. 21. 2008.</ref> <math>Y = F(X)+E</math>
* '''加法噪音Additive noise'''

* Linear noise:<ref>{{cite journal | last1 = Shimizu | first1 = Shohei | display-authors = etal | year = 2011 | title = DirectLiNGAM: A direct method for learning a linear non-Gaussian structural equation model | url = http://www.jmlr.org/papers/volume12/shimizu11a/shimizu11a.pdf | journal = The Journal of Machine Learning Research | volume = 12 | issue = | pages = 1225–1248 }}</ref> <math>Y = pX + qE</math>
* '''线性噪音Linear noise'''

* Post-non-linear:<ref>Zhang, Kun, and Aapo Hyvärinen. "[https://arxiv.org/pdf/1205.2599 On the identifiability of the post-nonlinear causal model]." Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence. AUAI Press, 2009.</ref> <math>Y = G(F(X)+E)</math>
* '''后非线性Post-non-linear（噪音）'''

* Heteroskedastic noise: <math>Y = F(X)+E.G(X)</math>
* '''异方差噪音Heteroskedastic noise'''

* Functional noise:<ref name="Mooij">Mooij, Joris M., et al. "[http://papers.nips.cc/paper/4173-probabilistic-latent-variable-models-for-distinguishing-between-cause-and-effect.pdf Probabilistic latent variable models for distinguishing between cause and effect]." NIPS. 2010.</ref> <math>Y = F(X,E)</math>
* '''功能性噪音Functional noise'''

The common assumption in these models are:

这些模型的共同假设是:
* There are no other causes of Y.
* Y 没有其他原因。

* X and E have no common causes.
* X 和 E 没有共同的原因。

* Distribution of cause is independent from causal mechanisms.
* 原因的分布独立于因果机制。

On an intuitive level, the idea is that the factorization of the joint distribution P(Cause, Effect) into P(Cause)*P(Effect | Cause) typically yields models of lower total complexity than the factorization into P(Effect)*P(Cause | Effect). Although the notion of “complexity” is intuitively appealing, it is not obvious how it should be precisely defined.<ref name="Mooij"/> A different family of methods attempt to discover causal "footprints" from large amounts of labeled data, and allow the prediction of more flexible causal relations.<ref>Lopez-Paz, David, et al. "[http://www.jmlr.org/proceedings/papers/v37/lopez-paz15.pdf Towards a learning theory of cause-effect inference]" ICML. 2015</ref>

在直观的层面上，这个想法是联合分布P(Cause, Effect) 到 P(Cause)*P(Effect | Cause)的因式分解通常产生的模型的总'''复杂性complexity '''低于到P(Effect)*P(Cause | Effect)的因式分解。尽管“复杂性”的概念在直觉上很吸引人，但是对于如何定义它却并不显而易见。另一种不同类族的方法尝试从大量标签过的数据中发现因果的“足迹”，并且允许预测更灵活的因果关系。
--ZC(讨论) 【审校】“这个想法是联合分布P(Cause, Effect) 到 P(Cause)*P(Effect | Cause)的因式分解通常产生的模型的总”改为“联合分布P(起因,结果)到P(起因)*P(结果|起因)拆分的主意通常产生模型的总”
--ZC(讨论) 【审校】“低于到P(Effect)*P(Cause | Effect)的因式分解”改为“低于将P(起因,结果)到P(结果)*P(起因|结果)的拆分”
--ZC(讨论) 【审校】“但是对于如何定义”改为“但对于应该如何精确定义”
--ZC(讨论) 【审校】“标签过”改为“被标记”

== In statistics and economics 在统计学和经济学领域==

{{Main|Causality#Statistics and economics}}

--[[用户:嘉树|嘉树]]（[[用户讨论:嘉树|讨论]]）本段似有错漏，英文词条和本段内容有一些不同。因此，（1）先写本段的翻译，（2）再写英文词条中有不同的地方，（3）最后整合一下。【】括起来的是在两个版本中需要照应和修改的部分。

In [[statistics]] and [[economics]], causality is often tested via [[regression analysis]]. Several methods can be used to distinguish actual causality from spurious correlations. First, economists constructing regression models establish the direction of causal relation based on economic theory (theory-driven econometrics). For example, if one studies the dependency between rainfall and the future price of a commodity, then theory (broadly construed) indicates that rainfall can influence prices, but futures prices cannot make changes to the amount of rain<ref>{{Cite book|last=Simon|first=Herbert|title=Models of Discovery|publisher=Springer|year=1977|location=Dordrecht|page=52}}</ref> . Second, the [[instrumental variables]] (IV) technique may be employed to remove any reverse causation by introducing a role for other variables (instruments) that are known to be unaffected by the dependent variable. Third, economists consider time precedence to choose appropriate model specification. Given that partial correlations are symmetrical, one cannot determine the direction of causal relation based on correlations only. Based on the notion of probabilistic view on causality, economists assume that causes must be prior in time than their effects. This leads to using the variables representing phenomena happening earlier as independent variables and developing econometric tests for causality (e.g., Granger-causality tests) applicable in time series analysis<ref>{{Cite book|last=Maziarz|first=Mariusz|title=The Philosophy of Causality in Economics: Causal Inferences and Policy Proposals|publisher=Routledge|year=2020|location=New York}}</ref>. Fifth, other regressors are included to ensure that [[confounding variable]]s are not causing a regressor to appear to be significant spuriously but, in the areas suffering from the problem of multicollinearity such as macroeconomics, it is in principle impossible to include all confounding factors and therefore econometric models are susceptible to the common-cause fallacy.<ref>{{Cite journal|last=Henschen|first=Tobias|date=2018|title=The in-principle inconclusiveness of causal evidence in macroeconomics|journal=European Journal for Philosophy of Science|volume=8|pages=709–733}}</ref>. Recently, the movement of design-based econometrics has popularized using natural experiments and quasi-experimental research designs to address the problem of spurious correlations.<ref>{{Cite book|last=Angrist Joshua & Pischke Jörn-Steffen|title=Mostly Harmless Econometrics: An Empiricist's Companion|publisher=Princeton University Press|year=2008|location=Princeton}}</ref>

在统计学和经济学中，因果关系通常通过回归分析来检验。有几种方法可以用来区分真实的因果关系和虚假的相关性。第一，经济学家根据经济理论('''理论驱动theory-driven'''的计量经济学)构建回归模型，从而确定因果关系的方向。
例如，如果研究降雨与未来商品价格之间的依赖关系，那么一个广义上建构的理论表明，降雨可以影响价格，但未来价格不能改变降雨量。<ref>{{Cite book|last=Simon|first=Herbert|title=Models of Discovery|publisher=Springer|year=1977|location=Dordrecht|page=52}}</ref> . 第二，'''工具变量instrumental variables(IV)'''技术可以通过引入其他已知不受因变量的影响的工具变量来消除任何反向因果关系。【第三，经济学家会考虑时间优先级来选择合适的具体模型。由于'''偏相关partial correlations'''是对称的，人们不能在相关的基础上确定因果关系的方向。经济学家基于因果关系的'''概率观点probabilistic view'''假设，原因必须在时间上优先于其结果。这导致经济学家使用较早发生的现象作为自变量，并开发适用于时间序列分析的因果关系检验计量经济方法（例如，'''格兰杰因果检验'''）<ref>{{Cite book|last=Maziarz|first=Mariusz|title=The Philosophy of Causality in Economics: Causal Inferences and Policy Proposals|publisher=Routledge|year=2020|location=New York}}</ref>。第五，有些做法包括了其他回归项，从而确保'''混淆变量confounding variables'''不会导致某个回归因素显得明显虚假，但遭受'''多重共线性multicollinearity'''问题困扰的领域，如宏观经济学，原则上不可能包括所有混淆因素，因此计量经济模型容易出现'''共因谬误common-cause fallacy'''<ref>{{Cite journal|last=Henschen|first=Tobias|date=2018|title=The in-principle inconclusiveness of causal evidence in macroeconomics|journal=European Journal for Philosophy of Science|volume=8|pages=709–733}}</ref>。近年来，'''以研究设计为基础的计量经济学design-based econometrics'''运动已经推广使用自然实验和准实验研究设计来解决'''虚假相关spurious correlations'''的问题<ref>{{Cite book|last=Angrist Joshua & Pischke Jörn-Steffen|title=Mostly Harmless Econometrics: An Empiricist's Companion|publisher=Princeton University Press|year=2008|location=Princeton}}</ref>。】

--[[用户:嘉树|嘉树]]（[[用户讨论:嘉树|讨论]]）英文词条的第三和第四：

Third, the principle that effects cannot precede causes can be invoked, by including on the right side of the regression only variables that precede in time the dependent variable.
Fourth, other regressors are included to ensure that confounding variables are not causing a regressor to spuriously appear to be significant. Correlation by coincidence, as opposed to correlation reflecting actual dependence of the underlying process, can be ruled out by using large samples and by performing cross validation to check that correlations are maintained on data that were not used in the regression.

【第三，通过在回归的右侧只包括时间上在因变量之前的变量，就可以使用结果不能优先于原因的原则。
第四，有些方法包括了其他回归因素，以确保'''混淆变量confounding variables'''不会导致一个回归项虚假地呈现显著。通过使用大样本和交叉验证检查在回归中未使用的数据上是否保持了相关性，可以排除巧合的，而不是反映实际依赖内在过程的相关性。】

--[[用户:嘉树|嘉树]]（[[用户讨论:嘉树|讨论]]）整合后的翻译：

在统计学和经济学中，因果关系通常通过回归分析来检验。有几种方法可以用来区分真实的因果关系和虚假的相关性。第一，经济学家根据经济理论('''理论驱动theory-driven'''的计量经济学)构建回归模型，从而确定因果关系的方向。例如，如果研究降雨与未来商品价格之间的依赖关系，那么一个广义上建构的理论表明，降雨可以影响价格，但未来价格不能改变降雨量。<ref>{{Cite book|last=Simon|first=Herbert|title=Models of Discovery|publisher=Springer|year=1977|location=Dordrecht|page=52}}</ref> . 第二，'''工具变量instrumental variables(IV)'''技术可以通过引入其他已知不受因变量的影响的工具变量来消除任何反向因果关系。第三，通过在回归的右侧只包括时间上在因变量之前的变量，就可以使用结果不能优先于原因的原则。由于'''偏相关partial correlations'''是对称的，人们不能在相关的基础上确定因果关系的方向。经济学家基于因果关系的'''概率观点probabilistic view'''假设，原因必须在时间上优先于其结果。这导致经济学家使用较早发生的现象作为自变量，并开发适用于时间序列分析的因果关系检验计量经济方法（例如，'''格兰杰因果检验'''）<ref>{{Cite book|last=Maziarz|first=Mariusz|title=The Philosophy of Causality in Economics: Causal Inferences and Policy Proposals|publisher=Routledge|year=2020|location=New York}}</ref>。第四，有些方法包括了其他回归因素，以确保'''混淆变量confounding variables'''不会导致一个回归项虚假地呈现显著。通过使用大样本和交叉验证检查在回归中未使用的数据上是否保持了相关性，可以排除巧合的，而不是反映实际依赖内在过程的相关性。但遭受'''多重共线性multicollinearity'''问题困扰的领域，如宏观经济学，原则上不可能包括所有混淆因素，因此计量经济模型容易出现'''共因谬误common-cause fallacy'''<ref>{{Cite journal|last=Henschen|first=Tobias|date=2018|title=The in-principle inconclusiveness of causal evidence in macroeconomics|journal=European Journal for Philosophy of Science|volume=8|pages=709–733}}</ref>。近年来，'''以研究设计为基础的计量经济学design-based econometrics'''运动已经推广使用自然实验和准实验研究设计来解决'''虚假相关spurious correlations'''的问题<ref>{{Cite book|last=Angrist Joshua & Pischke Jörn-Steffen|title=Mostly Harmless Econometrics: An Empiricist's Companion|publisher=Princeton University Press|year=2008|location=Princeton}}</ref>。

== In social science 在社会科学领域==

The social sciences have moved increasingly toward a quantitative framework for assessing causality. Much of this has been described as a means of providing greater rigor to social science methodology. Political science was significantly influenced by the publication of [[Designing Social Inquiry]], by Gary King, Robert Keohane, and Sidney Verba, in 1994. King, Keohane, and Verba (often abbreviated as KKV) recommended that researchers applying both quantitative and qualitative methods adopt the language of statistical inference to be clearer about their subjects of interest and units of analysis.<ref>{{Cite book|title=Designing social inquiry : scientific inference in qualitative research|first=Gary|last=King|date=2012|publisher=Princeton Univ. Press|isbn=978-0691034713|oclc=754613241}}</ref><ref name=":0">{{Cite journal|last=Mahoney|first=James|date=January 2010|title=After KKV|journal=World Politics|volume=62|issue=1|pages=120–147|jstor=40646193|doi=10.1017/S0043887109990220}}</ref> Proponents of quantitative methods have also increasingly adopted the [[Rubin causal model|potential outcomes framework]], developed by [[Donald Rubin]], as a standard for inferring causality.{{Citation needed|date=May 2019}}

社会科学越来越倾向评估因果关系的定量框架。框架中的很大一部分已经被描述为一种提供更严格的'''社会科学方法social science methodology'''的方式。1994年，'''加里·金Gary King'''、'''罗伯特 · 基奥汉Robert Keohane'''和'''西德尼 · 维尔巴Sidney Verba'''合著的《'''设计社会学问卷Designing Social Inquiry'''》对政治科学产生了重大影响。'''金、基奥汉，和维尔巴（通常缩写为 KKV）建议研究人员同时采用定量和定性的方法，采用统计推论的语言来更清楚地说明他们感兴趣的主题和分析的单位。King, Keohane, and Verba (often abbreviated as KKV) recommended that researchers applying both quantitative and qualitative methods adopt the language of statistical inference to be clearer about their subjects of interest and units of analysis.'''<ref>{{Cite book|title=Designing social inquiry : scientific inference in qualitative research|first=Gary|last=King|date=2012|publisher=Princeton Univ. Press|isbn=978-0691034713|oclc=754613241}}</ref><ref name=":0">{{Cite journal|last=Mahoney|first=James|date=January 2010|title=After KKV|journal=World Politics|volume=62|issue=1|pages=120–147|jstor=40646193|doi=10.1017/S0043887109990220}}</ref>定量方法的支持者也越来越多地采用'''唐纳德 · 鲁宾Donald Rubin'''开发的'''潜在结果框架potential outcomes framework'''作为推断因果关系的标准。
Debates over the appropriate application of quantitative methods to infer causality resulted in increased attention to the reproducibility of studies. Critics of widely-practiced methodologies argued that researchers have engaged in [[Data dredging|P hacking]] to publish articles on the basis of spurious correlations.<ref>{{Cite news|url=https://www.nytimes.com/2017/10/18/magazine/when-the-revolution-came-for-amy-cuddy.html|title=When the Revolution Came for Amy Cuddy|last=Dominus|first=Susan|date=18 October 2017|work=The New York Times|access-date=2019-03-02|language=en-US|issn=0362-4331}}</ref> To prevent this, some have advocated that researchers preregister their research designs prior to conducting to their studies so that they do not inadvertently overemphasize a non-reproducible finding that was not the initial subject of inquiry but was found to be statistically significant during data analysis.<ref>{{Cite web|url=https://www.americanscientist.org/article/the-statistical-crisis-in-science|title=The Statistical Crisis in Science|date=6 February 2017|website=American Scientist|language=en|access-date=2019-04-18}}</ref> Internal debates about methodology and reproducibility within the social sciences have at times been acrimonious.{{Citation needed|date=May 2019}}

合适地应用定量方法来推断因果关系的相关争论导致了对研究'''可重复性reproducibility'''的更多关注。对广泛被使用的方法持批评态度的人认为，研究人员利用'''数据挖掘Data dredging'''或'''p-hacking'''技术以在虚假相关的基础上发表文章<ref>{{Cite news|url=https://www.nytimes.com/2017/10/18/magazine/when-the-revolution-came-for-amy-cuddy.html|title=When the Revolution Came for Amy Cuddy|last=Dominus|first=Susan|date=18 October 2017|work=The New York Times|access-date=2019-03-02|language=en-US|issn=0362-4331}}</ref>。为了避免这种情况的发生，一些人主张研究人员在进行研究之前'''预注册preregister'''他们的研究设计，这样他们就不会无意中过分强调一项不可复制的发现，这项发现并非最初的调查对象，但在数据分析中被发现具有统计意义<ref>{{Cite web|url=https://www.americanscientist.org/article/the-statistical-crisis-in-science|title=The Statistical Crisis in Science|date=6 February 2017|website=American Scientist|language=en|access-date=2019-04-18}}</ref>。社会科学内部关于方法论和可重复性的争论有时是尖锐的{{Citation needed|date=May 2019}}。

While much of the emphasis remains on statistical inference in the potential outcomes framework, social science methodologists have developed new tools to conduct causal inference with both qualitative and quantitative methods, sometimes called a “mixed methods” approach.<ref>{{Cite book|url=https://books.google.com/books/about/Designing_and_Conducting_Mixed_Methods_R.html?id=YcdlPWPJRBcC|title=Designing and Conducting Mixed Methods Research|last=Creswell|first=John W.|last2=Clark|first2=Vicki L. Plano|date=2011|publisher=SAGE Publications|isbn=9781412975179|language=en}}</ref><ref>{{Cite book|url=https://www.cambridge.org/core/books/multimethod-social-science/286C2742878FBCC6225E2F10D6095A0C|title=Multi-Method Social Science by Jason Seawright|last=Seawright|first=Jason|date=September 2016|website=Cambridge Core|language=en|access-date=2019-04-18|doi=10.1017/CBO9781316160831|isbn=9781316160831}}</ref> Advocates of diverse methodological approaches argue that different methodologies are better suited to different subjects of study. Sociologist Herbert Smith and Political Scientists James Mahoney and Gary Goertz have cited the observation of Paul Holland, a statistician and author of the 1986 article “Statistics and Causal Inference,” that statistical inference is most appropriate for assessing the “effects of causes” rather than the “causes of effects.”<ref>{{Cite journal|last=Smith|first=Herbert L.|date=10 February 2014|title=Effects of Causes and Causes of Effects: Some Remarks from the Sociological Side|journal=Sociological Methods and Research|volume=43|issue=3|pages=406–415|doi=10.1177/0049124114521149|pmid=25477697|pmc=4251584}}</ref><ref>{{Cite journal|last=Goertz|first=Gary|last2=Mahoney|first2=James|date=2006|title=A Tale of Two Cultures: Contrasting Quantitative and Qualitative Research|journal=Political Analysis|language=en|volume=14|issue=3|pages=227–249|doi=10.1093/pan/mpj017|issn=1047-1987}}</ref> Qualitative methodologists have argued that formalized models of causation, including process tracing and fuzzy set theory, provide opportunities to infer causation through the identification of critical factors within case studies or through a process of comparison among several case studies.<ref name=":0" /> These methodologies are also valuable for subjects in which a limited number of potential observations or the presence of confounding variables would limit the applicability of statistical inference.{{Citation needed|date=May 2019}}

虽然在潜在结果框架中大部分重点仍然放在统计推论上，但社会科学方法学家已经开发出新的定性和定量方法来进行因果推断，有时被称为'''混合方法mixed methods'''。多种不同方法的支持者认为它更适合'''不同学科的研究different subjects of study'''。
--[[用户:嘉树|嘉树]]（[[用户讨论:嘉树|讨论]]）学科还是对象？
社会学家 Herbert Smith 和政治学家 James Mahoney 、 Gary Goertz 引用了统计学家 Paul Holland 的观察结果，Paul Holland在1986年发表了一篇名为《'''统计学和因果推断Statistics and Causal Inference'''》的文章，认为推论统计学最适合于评估“结果的原因”而不是“结果的原因”。定性方法学家认为，形式化的因果关系模型，包括'''过程追踪process tracing'''和'''模糊集理论fuzzy set theory'''，通过在某个案例研究内识别关键因素或在几个案例研究之间比较的过程提供了推断因果关系的机会。这些方法对于那些可能的观察数量有限或存在混淆变量从而限制统计推论适用性的课题也是有价值的。

== See also ==

参见
* [[Causal analysis]] 因果分析

* [[Granger causality]] 格兰杰因果分析

* [[Multivariate statistics]] 多元统计

* [[Partial least squares regression]] 偏最小二乘回归

* [[Pathogenesis]] 发病学

* [[Pathology]] 病理学

* [[Regression analysis]] 回归分析

* [[Transfer entropy]] 传递熵

== References ==

参考资料
{{Reflist}}

==Bibliography==

参考书目
* {{cite book |ref=what_if |last1=Hernán |first1=MA |author-link1=Miguel Hernán |last2=Robins |first2=JM |author-link2=James Robins |title=Causal Inference: What If |location=Barnsley |publisher=Boca Raton: Chapman & Hall/CRC |date=2020-01-21|url=https://www.hsph.harvard.edu/miguel-hernan/causal-inference-book/}}

==External links==

外部链接
{{Commons category}}

*[http://clopinet.com/isabelle/Projects/NIPS2013/ NIPS 2013 Workshop on Causality]

*[http://webdav.tuebingen.mpg.de/causality/ Causal inference at the Max-Planck-Institute for Intelligent Systems Tübingen]

{{Portal bar|Science}}

{{Use dmy dates|date=October 2019}}

== 编者推荐 ==
===集智课程推荐===
[https://campus.swarma.org/course/1078 社交网络中的因果推断] 本课程中，将简要介绍一些基本的因果推断策略，并聚焦社会网络分析中的因果推断问题，涉及社会网络实验设计、固定样本、工具变量和敏感度分析等。

===书籍推荐===
[https://book.douban.com/subject/33438811/ 为什么:关于因果关系的新科学] 在本书中，人工智能领域的权威专家Judea Pearl及其同事领导的因果关系革命突破多年的迷雾，厘清了知识的本质，确立了因果关系研究在科学探索中的核心地位。

[[Category:Causal inference| ]]

[[Category:Graphical models]]

类别: 图形模型
[[Category:Regression analysis]]

类别: 回归分析
[[Category:Inductive reasoning]]

类别: 归纳推理
[[Category:Philosophy of statistics]]

分类: 统计哲学
<noinclude>

This page was moved from [[wikipedia:en:Causal inference]]. Its edit history can be viewed at [[因果推断/edithistory]]</noinclude><noinclude>

This page was moved from [[mywiki:zh-cn:因果推断]]. Its edit history can be viewed at [[因果推断/edithistory]]</noinclude>

因果推断

2020-09-15T18:12:20Z

Zc1234567：

{{short description|Branch of statistics concerned with inferring causal relationships between variables}}

{{Expert needed|date=October 2019}}

'''Causal inference''' is the process of drawing a conclusion about a [[causal]] connection based on the conditions of the occurrence of an effect. The main difference between causal inference and inference of [[association (statistics)|association]] is that the former analyzes the response of the effect variable when the cause is changed.<ref name=Pearl_Journal>{{cite journal|last=Pearl|first=Judea|title=Causal inference in statistics: An overview|journal=Statistics Surveys|date=1 January 2009|volume=3|issue=|pages=96–146|doi=10.1214/09-SS057|url=http://ftp.cs.ucla.edu/pub/stat_ser/r350.pdf}}</ref><ref name=Morgan_book>{{cite book|last=Morgan|first=Stephen|author2=Winship, Chris|title=Counterfactuals and Causal inference|publisher=Cambridge University Press|year=2007|isbn=978-0-521-67193-4}}</ref> The science of why things occur is called [[etiology]]. Causal inference is an example of [[causal reasoning]].

'''因果推断Causal inference'''是根据某一效应发生的条件得出关于因果关系的结论的过程。因果推断与'''关联推理inference of association'''的主要区别在于前者分析在原因变化时结果变量的反应。研究事情为什么发生的科学叫做'''病因学etiology'''。因果推断是'''因果推理causal reasoning'''的一个例子。

--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“是根据某一效应发生的条件得出关于因果关系的结论的过程。”一句中的“根据”改为“基于”，“效应”改为“事件”，“因果关系的结论”改为“因果联系结论”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“的主要区别在于前者分析在原因变化时结果变量的反应。”一句中“在原因变化时”改为“了当原因改变时”,“反应”改为“响应”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“研究事情为什么发生的科学叫做”一句改为“研究事件因何而起的科学被称为”

==Definition定义==

Inferring the [[cause]] of something has been described as:

'''对某事原因的推断过程已经被描述为是:Inferring the [[cause]] of something has been described as:'''

--[[用户:嘉树|嘉树]]（[[用户讨论:嘉树|讨论]]） inferring是ing形式，因此译为“推断的过程”，存疑
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“对某事原因的推断过程已经被描述为是：”一句改为“推断某事原因的过程被描述为：”

*"...reason[ing] to the conclusion that something is, or is likely to be, the cause of something else".<ref name=EB>{{cite web|title=causal inference|url=http://www.britannica.com/EBchecked/topic/1442615/causal-inference|publisher=Encyclopædia Britannica, Inc.|accessdate=24 August 2014}}</ref>

*“推理得出某事是（或可能是）其他事情的原因这一结论的过程。”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“推理得出某事是（或可能是）其他事情的原因这一结论的过程。”一句改为“某事是（或可能是）其他事情的原因这一结论。”
*"Identification of the cause or causes of a phenomenon, by establishing covariation of cause and effect, a time-order relationship with the cause preceding the effect, and the elimination of plausible alternative causes."<ref name=psy>{{cite book|author1=John Shaughnessy|author2=Eugene Zechmeister|author3=Jeanne Zechmeister|title=Research Methods in Psychology|date=2000|publisher=McGraw-Hill Humanities/Social Sciences/Languages|isbn=978-0077825362|pages=Chapter 1 : Introduction|url=http://www.mhhe.com/socscience/psychology/shaugh/ch01_concepts.html|accessdate=24 August 2014|archive-url=https://web.archive.org/web/20141015135541/http://www.mhhe.com/socscience/psychology/shaugh/ch01_concepts.html|archive-date=15 October 2014|url-status=dead}}</ref>

*“通过建立因果的共变关系、建立原因先于结果的时间顺序关系，以及消除其他可能的替代原因的过程，从而对现象的一个或多个原因进行确定的过程。”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“通过建立因果的共变关系、建立原因先于结果的时间顺序关系，以及消除其他可能的替代原因的过程，从而对现象的一个或多个原因进行确定的过程。”一句改为“通过建立因果的共变模型，前因后果的时间顺序联系，以及消除其他可能的替代原因，从而对现象的一个或多个原因进行确认。”
==Methods 方法==

Epidemiological studies employ different [[epidemiological method]]s of collecting and measuring evidence of risk factors and effect and different ways of measuring association between the two. A [[hypothesis]] is formulated, and then [[Statistical hypothesis testing|tested with statistical methods]]. It is [[statistical inference]] that helps decide if data are due to chance, also called [[random variation]], or indeed correlated and if so how strongly. However, [[correlation does not imply causation]], so further methods must be used to infer causation.{{Citation needed|date=May 2019}}

'''流行病学epidemiological'''收集和衡量危险因素和结果，以及衡量危险因素和结果之间关系的方法与其他学科不同。一个假设提出来以后用'''统计学假设检验Statistical hypothesis testing'''。这种'''统计学推断statistical inference '''有助于判断数据是由偶然性引起的，也就是'''随机变异random variation'''，还是确实存在相关性，以及相关性有多强。然而，相关不意味着因果，因此必须进一步使用其他方法来推断因果关系。
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“收集和衡量危险因素和结果，以及衡量危险因素和结果之间关系的方法与其他学科不同。一个假设提出来以后用”一句改为“运用不同的流行病模型来收集和衡量危险因素和结果，以及判定两者之间的联系”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“一个假设提出来以后”一句改为“一个假说被提出来后”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“是由偶然性引起的，也就是”一句改为“是否由偶然性引起，也被称为”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“还是确实存在相关性，以及相关性有多强”一句改为“还是确实相关以及相关性的强弱”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“因此必须进一步使用其他方法来推断因果关系”一句改为“必须使用其他方法来推断其因果关系”
Common frameworks for causal inference are [[structural equation modeling]] and the [[Rubin causal model]].{{citation needed|date=August 2014}}

因果推断的常见框架有'''结构方程模型structural equation modeling'''和'''Rubin因果模型 Rubin causal model'''。

--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“因果推断的常见框架”一句改为“常见的因果推断框架有”
==In epidemiology 在流行病学中==

[[Epidemiology]] studies patterns of health and disease in defined populations of [[living beings]] in order to [[infer]] causes and effects. An association between an [[Exposure (environmental hazard)|exposure]] to a putative [[risk factor]] and a disease may be suggestive of, but is not equivalent to causality because [[correlation does not imply causation]]. Historically, [[Koch's postulates]] have been used since the 19th century to decide if a microorganism was the cause of a disease. In the 20th century the [[Bradford Hill criteria]], described in 1965<ref name="bh65">{{cite journal |last=Hill |first=Austin Bradford |year=1965 |title=The Environment and Disease: Association or Causation? |journal=[[Proceedings of the Royal Society of Medicine]] |volume=58 |pages=295–300 |url=http://www.edwardtufte.com/tufte/hill |pmid=14283879 |pmc=1898525 |issue=5 |doi=10.1177/003591576505800503}}</ref> have been used to assess causality of variables outside microbiology, although even these criteria are not exclusive ways to determine causality.

'''流行病学Epidemiology'''研究特定生物群体的健康和疾病'''模式patterns'''，以推断原因和结果。'''暴露exposure '''于一般认为的'''危险因素risk factor'''和疾病之间的联系可能被提出，但不等同于确认因果关系，因为相关不意味着因果。从历史上看，'''科赫法则 Koch's postulates'''从19世纪开始就被用来判断一种微生物是否是一种疾病的原因。在20世纪，'''布拉德福德·希尔准则Bradford Hill criteria'''（参见Bradford Hill 1965年的文章<ref name="bh65"></ref>中）已经被用来评估微生物学之外的变量的因果关系，尽管即使是这些标准也不是确定因果关系的唯一方法。

In [[molecular epidemiology]] the phenomena studied are on a [[molecular biology]] level, including genetics, where [[biomarkers]] are evidence of cause or effects.

'''分子流行病学molecular epidemiology'''中研究的现象是在'''分子生物学'''水平上的，也涵盖了遗传学。而遗传学中的'''生物标志物biomarkers'''就是原因或结果的证据。

A recent trend{{when|date=August 2014}} is to identify [[evidence]] for influence of the exposure on [[molecular pathology]] within diseased [[Tissue (biology)|tissue]] or cells, in the emerging interdisciplinary field of [[molecular pathological epidemiology]] (MPE).{{third-party-inline|date=August 2014}} Linking the exposure to molecular pathologic signatures of the disease can help to assess causality. {{third-party-inline|date=August 2014}} Considering the inherent nature of [[heterogeneity]] of a given disease, the unique disease principle, disease phenotyping and subtyping are trends in biomedical and [[public health]] sciences, exemplified as [[personalized medicine]] and [[precision medicine]].{{third-party-inline|date=August 2014}}

在新兴的'''分子病理流行病学molecular pathological epidemiology (MPE)'''交叉学科领域，最近的一个趋势（截至2014年）是确定在病变组织或细胞内，'''暴露exposure '''在'''分子病理学molecular pathology'''上的影响。将暴露与疾病的分子病理特征联系起来可以帮助因果关系的评估。鉴于给定疾病的'''异质性'''的固有特征、独特的疾病原理等，疾病'''表现型phenotyping'''和'''亚型subtyping '''现在是生物医学和'''公共卫生科学public health'''的趋势，例证包括'''个体化医学personalized medicine'''和'''精准医学precision medicine'''等。

==In computer science在计算机科学领域==

Determination of cause and effect from joint observational data for two time-independent variables, say X and Y, has been tackled using asymmetry between evidence for some model in the directions, X → Y and Y → X. The primary approaches are based on [[Algorithmic information theory]] models and noise models.{{Citation needed|date=May 2019}}

确定两个时间独立变量：X 和 Y 的联合观测数据因果关系的问题已经被解决了，方法是利用 X → Y 和 Y → X 方向上某些模型的证据不对称性。主要的方法基于'''算法信息理论Algorithmic information theory'''模型和'''噪声模型noise models'''。

===Algorithmic information models算法信息模型===

Compare two programs, both of which output both X and Y.

比较两个同时输出 X 和 Y 的程序。
* Store Y and a compressed form of X in terms of uncompressed Y.

* Store X and a compressed form of Y in terms of uncompressed X.

* 用未压缩的 X 来存储 X 和压缩形式的 Y 。

The shortest such program implies the uncompressed stored variable more-likely causes the computed variable.<ref>Kailash Budhathoki and Jilles Vreeken "[http://eda.mmci.uni-saarland.de/pubs/2016/origo-budhathoki,vreeken.pdf Causal Inference by Compression]" 2016 IEEE 16th International Conference on Data Mining (ICDM)</ref><ref>{{Cite journal |doi = 10.1007/s10115-018-1286-7|title = Telling cause from effect by local and global regression|journal = Knowledge and Information Systems|year = 2018|last1 = Marx|first1 = Alexander|last2 = Vreeken|first2 = Jilles|volume=60|issue = 3|pages=1277–1305|doi-access = free}}</ref>

最短的这种程序意味着，更有可能是未压缩的'''存储变量stored variable'''导致了'''计算出的变量computed variable'''。

===Noise models噪音模型===

Incorporate an independent noise term in the model to compare the evidences of the two directions.

在模型中引入一个独立的噪声项，以比较两个方向的证据。

Here are some of the noise models for the hypothesis Y → X with the noise E:

下面是一些支持 Y → X 假设且具有噪声 E 的噪声模型:
* Additive noise:<ref>Hoyer, Patrik O., et al. "[https://papers.nips.cc/paper/3548-nonlinear-causal-discovery-with-additive-noise-models.pdf Nonlinear causal discovery with additive noise models]." NIPS. Vol. 21. 2008.</ref> <math>Y = F(X)+E</math>
* '''加法噪音Additive noise'''

* Linear noise:<ref>{{cite journal | last1 = Shimizu | first1 = Shohei | display-authors = etal | year = 2011 | title = DirectLiNGAM: A direct method for learning a linear non-Gaussian structural equation model | url = http://www.jmlr.org/papers/volume12/shimizu11a/shimizu11a.pdf | journal = The Journal of Machine Learning Research | volume = 12 | issue = | pages = 1225–1248 }}</ref> <math>Y = pX + qE</math>
* '''线性噪音Linear noise'''

* Post-non-linear:<ref>Zhang, Kun, and Aapo Hyvärinen. "[https://arxiv.org/pdf/1205.2599 On the identifiability of the post-nonlinear causal model]." Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence. AUAI Press, 2009.</ref> <math>Y = G(F(X)+E)</math>
* '''后非线性Post-non-linear（噪音）'''

* Heteroskedastic noise: <math>Y = F(X)+E.G(X)</math>
* '''异方差噪音Heteroskedastic noise'''

* Functional noise:<ref name="Mooij">Mooij, Joris M., et al. "[http://papers.nips.cc/paper/4173-probabilistic-latent-variable-models-for-distinguishing-between-cause-and-effect.pdf Probabilistic latent variable models for distinguishing between cause and effect]." NIPS. 2010.</ref> <math>Y = F(X,E)</math>
* '''功能性噪音Functional noise'''

The common assumption in these models are:

这些模型的共同假设是:
* There are no other causes of Y.
* Y 没有其他原因。

* X and E have no common causes.
* X 和 E 没有共同的原因。

* Distribution of cause is independent from causal mechanisms.
* 原因的分布独立于因果机制。

On an intuitive level, the idea is that the factorization of the joint distribution P(Cause, Effect) into P(Cause)*P(Effect | Cause) typically yields models of lower total complexity than the factorization into P(Effect)*P(Cause | Effect). Although the notion of “complexity” is intuitively appealing, it is not obvious how it should be precisely defined.<ref name="Mooij"/> A different family of methods attempt to discover causal "footprints" from large amounts of labeled data, and allow the prediction of more flexible causal relations.<ref>Lopez-Paz, David, et al. "[http://www.jmlr.org/proceedings/papers/v37/lopez-paz15.pdf Towards a learning theory of cause-effect inference]" ICML. 2015</ref>

在直观的层面上，这个想法是联合分布P(Cause, Effect) 到 P(Cause)*P(Effect | Cause)的因式分解通常产生的模型的总'''复杂性complexity '''低于到P(Effect)*P(Cause | Effect)的因式分解。尽管“复杂性”的概念在直觉上很吸引人，但是对于如何定义它却并不显而易见。另一种不同类族的方法尝试从大量标签过的数据中发现因果的“足迹”，并且允许预测更灵活的因果关系。

== In statistics and economics 在统计学和经济学领域==

{{Main|Causality#Statistics and economics}}

--[[用户:嘉树|嘉树]]（[[用户讨论:嘉树|讨论]]）本段似有错漏，英文词条和本段内容有一些不同。因此，（1）先写本段的翻译，（2）再写英文词条中有不同的地方，（3）最后整合一下。【】括起来的是在两个版本中需要照应和修改的部分。

In [[statistics]] and [[economics]], causality is often tested via [[regression analysis]]. Several methods can be used to distinguish actual causality from spurious correlations. First, economists constructing regression models establish the direction of causal relation based on economic theory (theory-driven econometrics). For example, if one studies the dependency between rainfall and the future price of a commodity, then theory (broadly construed) indicates that rainfall can influence prices, but futures prices cannot make changes to the amount of rain<ref>{{Cite book|last=Simon|first=Herbert|title=Models of Discovery|publisher=Springer|year=1977|location=Dordrecht|page=52}}</ref> . Second, the [[instrumental variables]] (IV) technique may be employed to remove any reverse causation by introducing a role for other variables (instruments) that are known to be unaffected by the dependent variable. Third, economists consider time precedence to choose appropriate model specification. Given that partial correlations are symmetrical, one cannot determine the direction of causal relation based on correlations only. Based on the notion of probabilistic view on causality, economists assume that causes must be prior in time than their effects. This leads to using the variables representing phenomena happening earlier as independent variables and developing econometric tests for causality (e.g., Granger-causality tests) applicable in time series analysis<ref>{{Cite book|last=Maziarz|first=Mariusz|title=The Philosophy of Causality in Economics: Causal Inferences and Policy Proposals|publisher=Routledge|year=2020|location=New York}}</ref>. Fifth, other regressors are included to ensure that [[confounding variable]]s are not causing a regressor to appear to be significant spuriously but, in the areas suffering from the problem of multicollinearity such as macroeconomics, it is in principle impossible to include all confounding factors and therefore econometric models are susceptible to the common-cause fallacy.<ref>{{Cite journal|last=Henschen|first=Tobias|date=2018|title=The in-principle inconclusiveness of causal evidence in macroeconomics|journal=European Journal for Philosophy of Science|volume=8|pages=709–733}}</ref>. Recently, the movement of design-based econometrics has popularized using natural experiments and quasi-experimental research designs to address the problem of spurious correlations.<ref>{{Cite book|last=Angrist Joshua & Pischke Jörn-Steffen|title=Mostly Harmless Econometrics: An Empiricist's Companion|publisher=Princeton University Press|year=2008|location=Princeton}}</ref>

在统计学和经济学中，因果关系通常通过回归分析来检验。有几种方法可以用来区分真实的因果关系和虚假的相关性。第一，经济学家根据经济理论('''理论驱动theory-driven'''的计量经济学)构建回归模型，从而确定因果关系的方向。
例如，如果研究降雨与未来商品价格之间的依赖关系，那么一个广义上建构的理论表明，降雨可以影响价格，但未来价格不能改变降雨量。<ref>{{Cite book|last=Simon|first=Herbert|title=Models of Discovery|publisher=Springer|year=1977|location=Dordrecht|page=52}}</ref> . 第二，'''工具变量instrumental variables(IV)'''技术可以通过引入其他已知不受因变量的影响的工具变量来消除任何反向因果关系。【第三，经济学家会考虑时间优先级来选择合适的具体模型。由于'''偏相关partial correlations'''是对称的，人们不能在相关的基础上确定因果关系的方向。经济学家基于因果关系的'''概率观点probabilistic view'''假设，原因必须在时间上优先于其结果。这导致经济学家使用较早发生的现象作为自变量，并开发适用于时间序列分析的因果关系检验计量经济方法（例如，'''格兰杰因果检验'''）<ref>{{Cite book|last=Maziarz|first=Mariusz|title=The Philosophy of Causality in Economics: Causal Inferences and Policy Proposals|publisher=Routledge|year=2020|location=New York}}</ref>。第五，有些做法包括了其他回归项，从而确保'''混淆变量confounding variables'''不会导致某个回归因素显得明显虚假，但遭受'''多重共线性multicollinearity'''问题困扰的领域，如宏观经济学，原则上不可能包括所有混淆因素，因此计量经济模型容易出现'''共因谬误common-cause fallacy'''<ref>{{Cite journal|last=Henschen|first=Tobias|date=2018|title=The in-principle inconclusiveness of causal evidence in macroeconomics|journal=European Journal for Philosophy of Science|volume=8|pages=709–733}}</ref>。近年来，'''以研究设计为基础的计量经济学design-based econometrics'''运动已经推广使用自然实验和准实验研究设计来解决'''虚假相关spurious correlations'''的问题<ref>{{Cite book|last=Angrist Joshua & Pischke Jörn-Steffen|title=Mostly Harmless Econometrics: An Empiricist's Companion|publisher=Princeton University Press|year=2008|location=Princeton}}</ref>。】

--[[用户:嘉树|嘉树]]（[[用户讨论:嘉树|讨论]]）英文词条的第三和第四：

Third, the principle that effects cannot precede causes can be invoked, by including on the right side of the regression only variables that precede in time the dependent variable.
Fourth, other regressors are included to ensure that confounding variables are not causing a regressor to spuriously appear to be significant. Correlation by coincidence, as opposed to correlation reflecting actual dependence of the underlying process, can be ruled out by using large samples and by performing cross validation to check that correlations are maintained on data that were not used in the regression.

【第三，通过在回归的右侧只包括时间上在因变量之前的变量，就可以使用结果不能优先于原因的原则。
第四，有些方法包括了其他回归因素，以确保'''混淆变量confounding variables'''不会导致一个回归项虚假地呈现显著。通过使用大样本和交叉验证检查在回归中未使用的数据上是否保持了相关性，可以排除巧合的，而不是反映实际依赖内在过程的相关性。】

--[[用户:嘉树|嘉树]]（[[用户讨论:嘉树|讨论]]）整合后的翻译：

在统计学和经济学中，因果关系通常通过回归分析来检验。有几种方法可以用来区分真实的因果关系和虚假的相关性。第一，经济学家根据经济理论('''理论驱动theory-driven'''的计量经济学)构建回归模型，从而确定因果关系的方向。例如，如果研究降雨与未来商品价格之间的依赖关系，那么一个广义上建构的理论表明，降雨可以影响价格，但未来价格不能改变降雨量。<ref>{{Cite book|last=Simon|first=Herbert|title=Models of Discovery|publisher=Springer|year=1977|location=Dordrecht|page=52}}</ref> . 第二，'''工具变量instrumental variables(IV)'''技术可以通过引入其他已知不受因变量的影响的工具变量来消除任何反向因果关系。第三，通过在回归的右侧只包括时间上在因变量之前的变量，就可以使用结果不能优先于原因的原则。由于'''偏相关partial correlations'''是对称的，人们不能在相关的基础上确定因果关系的方向。经济学家基于因果关系的'''概率观点probabilistic view'''假设，原因必须在时间上优先于其结果。这导致经济学家使用较早发生的现象作为自变量，并开发适用于时间序列分析的因果关系检验计量经济方法（例如，'''格兰杰因果检验'''）<ref>{{Cite book|last=Maziarz|first=Mariusz|title=The Philosophy of Causality in Economics: Causal Inferences and Policy Proposals|publisher=Routledge|year=2020|location=New York}}</ref>。第四，有些方法包括了其他回归因素，以确保'''混淆变量confounding variables'''不会导致一个回归项虚假地呈现显著。通过使用大样本和交叉验证检查在回归中未使用的数据上是否保持了相关性，可以排除巧合的，而不是反映实际依赖内在过程的相关性。但遭受'''多重共线性multicollinearity'''问题困扰的领域，如宏观经济学，原则上不可能包括所有混淆因素，因此计量经济模型容易出现'''共因谬误common-cause fallacy'''<ref>{{Cite journal|last=Henschen|first=Tobias|date=2018|title=The in-principle inconclusiveness of causal evidence in macroeconomics|journal=European Journal for Philosophy of Science|volume=8|pages=709–733}}</ref>。近年来，'''以研究设计为基础的计量经济学design-based econometrics'''运动已经推广使用自然实验和准实验研究设计来解决'''虚假相关spurious correlations'''的问题<ref>{{Cite book|last=Angrist Joshua & Pischke Jörn-Steffen|title=Mostly Harmless Econometrics: An Empiricist's Companion|publisher=Princeton University Press|year=2008|location=Princeton}}</ref>。

== In social science 在社会科学领域==

The social sciences have moved increasingly toward a quantitative framework for assessing causality. Much of this has been described as a means of providing greater rigor to social science methodology. Political science was significantly influenced by the publication of [[Designing Social Inquiry]], by Gary King, Robert Keohane, and Sidney Verba, in 1994. King, Keohane, and Verba (often abbreviated as KKV) recommended that researchers applying both quantitative and qualitative methods adopt the language of statistical inference to be clearer about their subjects of interest and units of analysis.<ref>{{Cite book|title=Designing social inquiry : scientific inference in qualitative research|first=Gary|last=King|date=2012|publisher=Princeton Univ. Press|isbn=978-0691034713|oclc=754613241}}</ref><ref name=":0">{{Cite journal|last=Mahoney|first=James|date=January 2010|title=After KKV|journal=World Politics|volume=62|issue=1|pages=120–147|jstor=40646193|doi=10.1017/S0043887109990220}}</ref> Proponents of quantitative methods have also increasingly adopted the [[Rubin causal model|potential outcomes framework]], developed by [[Donald Rubin]], as a standard for inferring causality.{{Citation needed|date=May 2019}}

社会科学越来越倾向评估因果关系的定量框架。框架中的很大一部分已经被描述为一种提供更严格的'''社会科学方法social science methodology'''的方式。1994年，'''加里·金Gary King'''、'''罗伯特 · 基奥汉Robert Keohane'''和'''西德尼 · 维尔巴Sidney Verba'''合著的《'''设计社会学问卷Designing Social Inquiry'''》对政治科学产生了重大影响。'''金、基奥汉，和维尔巴（通常缩写为 KKV）建议研究人员同时采用定量和定性的方法，采用统计推论的语言来更清楚地说明他们感兴趣的主题和分析的单位。King, Keohane, and Verba (often abbreviated as KKV) recommended that researchers applying both quantitative and qualitative methods adopt the language of statistical inference to be clearer about their subjects of interest and units of analysis.'''<ref>{{Cite book|title=Designing social inquiry : scientific inference in qualitative research|first=Gary|last=King|date=2012|publisher=Princeton Univ. Press|isbn=978-0691034713|oclc=754613241}}</ref><ref name=":0">{{Cite journal|last=Mahoney|first=James|date=January 2010|title=After KKV|journal=World Politics|volume=62|issue=1|pages=120–147|jstor=40646193|doi=10.1017/S0043887109990220}}</ref>定量方法的支持者也越来越多地采用'''唐纳德 · 鲁宾Donald Rubin'''开发的'''潜在结果框架potential outcomes framework'''作为推断因果关系的标准。
Debates over the appropriate application of quantitative methods to infer causality resulted in increased attention to the reproducibility of studies. Critics of widely-practiced methodologies argued that researchers have engaged in [[Data dredging|P hacking]] to publish articles on the basis of spurious correlations.<ref>{{Cite news|url=https://www.nytimes.com/2017/10/18/magazine/when-the-revolution-came-for-amy-cuddy.html|title=When the Revolution Came for Amy Cuddy|last=Dominus|first=Susan|date=18 October 2017|work=The New York Times|access-date=2019-03-02|language=en-US|issn=0362-4331}}</ref> To prevent this, some have advocated that researchers preregister their research designs prior to conducting to their studies so that they do not inadvertently overemphasize a non-reproducible finding that was not the initial subject of inquiry but was found to be statistically significant during data analysis.<ref>{{Cite web|url=https://www.americanscientist.org/article/the-statistical-crisis-in-science|title=The Statistical Crisis in Science|date=6 February 2017|website=American Scientist|language=en|access-date=2019-04-18}}</ref> Internal debates about methodology and reproducibility within the social sciences have at times been acrimonious.{{Citation needed|date=May 2019}}

合适地应用定量方法来推断因果关系的相关争论导致了对研究'''可重复性reproducibility'''的更多关注。对广泛被使用的方法持批评态度的人认为，研究人员利用'''数据挖掘Data dredging'''或'''p-hacking'''技术以在虚假相关的基础上发表文章<ref>{{Cite news|url=https://www.nytimes.com/2017/10/18/magazine/when-the-revolution-came-for-amy-cuddy.html|title=When the Revolution Came for Amy Cuddy|last=Dominus|first=Susan|date=18 October 2017|work=The New York Times|access-date=2019-03-02|language=en-US|issn=0362-4331}}</ref>。为了避免这种情况的发生，一些人主张研究人员在进行研究之前'''预注册preregister'''他们的研究设计，这样他们就不会无意中过分强调一项不可复制的发现，这项发现并非最初的调查对象，但在数据分析中被发现具有统计意义<ref>{{Cite web|url=https://www.americanscientist.org/article/the-statistical-crisis-in-science|title=The Statistical Crisis in Science|date=6 February 2017|website=American Scientist|language=en|access-date=2019-04-18}}</ref>。社会科学内部关于方法论和可重复性的争论有时是尖锐的{{Citation needed|date=May 2019}}。

While much of the emphasis remains on statistical inference in the potential outcomes framework, social science methodologists have developed new tools to conduct causal inference with both qualitative and quantitative methods, sometimes called a “mixed methods” approach.<ref>{{Cite book|url=https://books.google.com/books/about/Designing_and_Conducting_Mixed_Methods_R.html?id=YcdlPWPJRBcC|title=Designing and Conducting Mixed Methods Research|last=Creswell|first=John W.|last2=Clark|first2=Vicki L. Plano|date=2011|publisher=SAGE Publications|isbn=9781412975179|language=en}}</ref><ref>{{Cite book|url=https://www.cambridge.org/core/books/multimethod-social-science/286C2742878FBCC6225E2F10D6095A0C|title=Multi-Method Social Science by Jason Seawright|last=Seawright|first=Jason|date=September 2016|website=Cambridge Core|language=en|access-date=2019-04-18|doi=10.1017/CBO9781316160831|isbn=9781316160831}}</ref> Advocates of diverse methodological approaches argue that different methodologies are better suited to different subjects of study. Sociologist Herbert Smith and Political Scientists James Mahoney and Gary Goertz have cited the observation of Paul Holland, a statistician and author of the 1986 article “Statistics and Causal Inference,” that statistical inference is most appropriate for assessing the “effects of causes” rather than the “causes of effects.”<ref>{{Cite journal|last=Smith|first=Herbert L.|date=10 February 2014|title=Effects of Causes and Causes of Effects: Some Remarks from the Sociological Side|journal=Sociological Methods and Research|volume=43|issue=3|pages=406–415|doi=10.1177/0049124114521149|pmid=25477697|pmc=4251584}}</ref><ref>{{Cite journal|last=Goertz|first=Gary|last2=Mahoney|first2=James|date=2006|title=A Tale of Two Cultures: Contrasting Quantitative and Qualitative Research|journal=Political Analysis|language=en|volume=14|issue=3|pages=227–249|doi=10.1093/pan/mpj017|issn=1047-1987}}</ref> Qualitative methodologists have argued that formalized models of causation, including process tracing and fuzzy set theory, provide opportunities to infer causation through the identification of critical factors within case studies or through a process of comparison among several case studies.<ref name=":0" /> These methodologies are also valuable for subjects in which a limited number of potential observations or the presence of confounding variables would limit the applicability of statistical inference.{{Citation needed|date=May 2019}}

虽然在潜在结果框架中大部分重点仍然放在统计推论上，但社会科学方法学家已经开发出新的定性和定量方法来进行因果推断，有时被称为'''混合方法mixed methods'''。多种不同方法的支持者认为它更适合'''不同学科的研究different subjects of study'''。
--[[用户:嘉树|嘉树]]（[[用户讨论:嘉树|讨论]]）学科还是对象？
社会学家 Herbert Smith 和政治学家 James Mahoney 、 Gary Goertz 引用了统计学家 Paul Holland 的观察结果，Paul Holland在1986年发表了一篇名为《'''统计学和因果推断Statistics and Causal Inference'''》的文章，认为推论统计学最适合于评估“结果的原因”而不是“结果的原因”。定性方法学家认为，形式化的因果关系模型，包括'''过程追踪process tracing'''和'''模糊集理论fuzzy set theory'''，通过在某个案例研究内识别关键因素或在几个案例研究之间比较的过程提供了推断因果关系的机会。这些方法对于那些可能的观察数量有限或存在混淆变量从而限制统计推论适用性的课题也是有价值的。

== See also ==

参见
* [[Causal analysis]] 因果分析

* [[Granger causality]] 格兰杰因果分析

* [[Multivariate statistics]] 多元统计

* [[Partial least squares regression]] 偏最小二乘回归

* [[Pathogenesis]] 发病学

* [[Pathology]] 病理学

* [[Regression analysis]] 回归分析

* [[Transfer entropy]] 传递熵

== References ==

参考资料
{{Reflist}}

==Bibliography==

参考书目
* {{cite book |ref=what_if |last1=Hernán |first1=MA |author-link1=Miguel Hernán |last2=Robins |first2=JM |author-link2=James Robins |title=Causal Inference: What If |location=Barnsley |publisher=Boca Raton: Chapman & Hall/CRC |date=2020-01-21|url=https://www.hsph.harvard.edu/miguel-hernan/causal-inference-book/}}

==External links==

外部链接
{{Commons category}}

*[http://clopinet.com/isabelle/Projects/NIPS2013/ NIPS 2013 Workshop on Causality]

*[http://webdav.tuebingen.mpg.de/causality/ Causal inference at the Max-Planck-Institute for Intelligent Systems Tübingen]

{{Portal bar|Science}}

{{Use dmy dates|date=October 2019}}

== 编者推荐 ==
===集智课程推荐===
[https://campus.swarma.org/course/1078 社交网络中的因果推断] 本课程中，将简要介绍一些基本的因果推断策略，并聚焦社会网络分析中的因果推断问题，涉及社会网络实验设计、固定样本、工具变量和敏感度分析等。

===书籍推荐===
[https://book.douban.com/subject/33438811/ 为什么:关于因果关系的新科学] 在本书中，人工智能领域的权威专家Judea Pearl及其同事领导的因果关系革命突破多年的迷雾，厘清了知识的本质，确立了因果关系研究在科学探索中的核心地位。

[[Category:Causal inference| ]]

[[Category:Graphical models]]

类别: 图形模型
[[Category:Regression analysis]]

类别: 回归分析
[[Category:Inductive reasoning]]

类别: 归纳推理
[[Category:Philosophy of statistics]]

分类: 统计哲学
<noinclude>

This page was moved from [[wikipedia:en:Causal inference]]. Its edit history can be viewed at [[因果推断/edithistory]]</noinclude><noinclude>

This page was moved from [[mywiki:zh-cn:因果推断]]. Its edit history can be viewed at [[因果推断/edithistory]]</noinclude>

因果推断

2020-09-14T13:56:09Z

Zc1234567：

{{short description|Branch of statistics concerned with inferring causal relationships between variables}}

{{Expert needed|date=October 2019}}

'''Causal inference''' is the process of drawing a conclusion about a [[causal]] connection based on the conditions of the occurrence of an effect. The main difference between causal inference and inference of [[association (statistics)|association]] is that the former analyzes the response of the effect variable when the cause is changed.<ref name=Pearl_Journal>{{cite journal|last=Pearl|first=Judea|title=Causal inference in statistics: An overview|journal=Statistics Surveys|date=1 January 2009|volume=3|issue=|pages=96–146|doi=10.1214/09-SS057|url=http://ftp.cs.ucla.edu/pub/stat_ser/r350.pdf}}</ref><ref name=Morgan_book>{{cite book|last=Morgan|first=Stephen|author2=Winship, Chris|title=Counterfactuals and Causal inference|publisher=Cambridge University Press|year=2007|isbn=978-0-521-67193-4}}</ref> The science of why things occur is called [[etiology]]. Causal inference is an example of [[causal reasoning]].

'''因果推断Causal inference'''是根据某一效应发生的条件得出关于因果关系的结论的过程。因果推断与'''关联推理inference of association'''的主要区别在于前者分析在原因变化时结果变量的反应。研究事情为什么发生的科学叫做'''病因学etiology'''。因果推断是'''因果推理causal reasoning'''的一个例子。

--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“是根据某一效应发生的条件得出关于因果关系的结论的过程。”一句中的“根据”改为“基于”，“效应”改为“事件”，“因果关系的结论”改为“因果联系结论”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“的主要区别在于前者分析在原因变化时结果变量的反应。”一句中“在原因变化时”改为“了当原因改变时”,“反应”改为“响应”
--[[用户:ZC|ZC]]([[用户讨论:ZC|讨论]]) 【审校】“研究事情为什么发生的科学叫做”一句改为“研究事件因何而起的科学被称为”

==Definition定义==

Inferring the [[cause]] of something has been described as:

'''对某事原因的推断过程已经被描述为是:Inferring the [[cause]] of something has been described as:'''

--[[用户:嘉树|嘉树]]（[[用户讨论:嘉树|讨论]]） inferring是ing形式，因此译为“推断的过程”，存疑

*"...reason[ing] to the conclusion that something is, or is likely to be, the cause of something else".<ref name=EB>{{cite web|title=causal inference|url=http://www.britannica.com/EBchecked/topic/1442615/causal-inference|publisher=Encyclopædia Britannica, Inc.|accessdate=24 August 2014}}</ref>

*“推理得出某事是（或可能是）其他事情的原因这一结论的过程。”

*"Identification of the cause or causes of a phenomenon, by establishing covariation of cause and effect, a time-order relationship with the cause preceding the effect, and the elimination of plausible alternative causes."<ref name=psy>{{cite book|author1=John Shaughnessy|author2=Eugene Zechmeister|author3=Jeanne Zechmeister|title=Research Methods in Psychology|date=2000|publisher=McGraw-Hill Humanities/Social Sciences/Languages|isbn=978-0077825362|pages=Chapter 1 : Introduction|url=http://www.mhhe.com/socscience/psychology/shaugh/ch01_concepts.html|accessdate=24 August 2014|archive-url=https://web.archive.org/web/20141015135541/http://www.mhhe.com/socscience/psychology/shaugh/ch01_concepts.html|archive-date=15 October 2014|url-status=dead}}</ref>

*“通过建立因果的共变关系、建立原因先于结果的时间顺序关系，以及消除其他可能的替代原因的过程，从而对现象的一个或多个原因进行确定的过程。”

==Methods 方法==

Epidemiological studies employ different [[epidemiological method]]s of collecting and measuring evidence of risk factors and effect and different ways of measuring association between the two. A [[hypothesis]] is formulated, and then [[Statistical hypothesis testing|tested with statistical methods]]. It is [[statistical inference]] that helps decide if data are due to chance, also called [[random variation]], or indeed correlated and if so how strongly. However, [[correlation does not imply causation]], so further methods must be used to infer causation.{{Citation needed|date=May 2019}}

'''流行病学epidemiological'''收集和衡量危险因素和结果，以及衡量危险因素和结果之间关系的方法与其他学科不同。一个假设提出来以后用'''统计学假设检验Statistical hypothesis testing'''。这种'''统计学推断statistical inference '''有助于判断数据是由偶然性引起的，也就是'''随机变异random variation'''，还是确实存在相关性，以及相关性有多强。然而，相关不意味着因果，因此必须进一步使用其他方法来推断因果关系。

Common frameworks for causal inference are [[structural equation modeling]] and the [[Rubin causal model]].{{citation needed|date=August 2014}}

因果推断的常见框架有'''结构方程模型structural equation modeling'''和'''Rubin因果模型 Rubin causal model'''。

==In epidemiology 在流行病学中==

[[Epidemiology]] studies patterns of health and disease in defined populations of [[living beings]] in order to [[infer]] causes and effects. An association between an [[Exposure (environmental hazard)|exposure]] to a putative [[risk factor]] and a disease may be suggestive of, but is not equivalent to causality because [[correlation does not imply causation]]. Historically, [[Koch's postulates]] have been used since the 19th century to decide if a microorganism was the cause of a disease. In the 20th century the [[Bradford Hill criteria]], described in 1965<ref name="bh65">{{cite journal |last=Hill |first=Austin Bradford |year=1965 |title=The Environment and Disease: Association or Causation? |journal=[[Proceedings of the Royal Society of Medicine]] |volume=58 |pages=295–300 |url=http://www.edwardtufte.com/tufte/hill |pmid=14283879 |pmc=1898525 |issue=5 |doi=10.1177/003591576505800503}}</ref> have been used to assess causality of variables outside microbiology, although even these criteria are not exclusive ways to determine causality.

'''流行病学Epidemiology'''研究特定生物群体的健康和疾病'''模式patterns'''，以推断原因和结果。'''暴露exposure '''于一般认为的'''危险因素risk factor'''和疾病之间的联系可能被提出，但不等同于确认因果关系，因为相关不意味着因果。从历史上看，'''科赫法则 Koch's postulates'''从19世纪开始就被用来判断一种微生物是否是一种疾病的原因。在20世纪，'''布拉德福德·希尔准则Bradford Hill criteria'''（参见Bradford Hill 1965年的文章<ref name="bh65"></ref>中）已经被用来评估微生物学之外的变量的因果关系，尽管即使是这些标准也不是确定因果关系的唯一方法。

In [[molecular epidemiology]] the phenomena studied are on a [[molecular biology]] level, including genetics, where [[biomarkers]] are evidence of cause or effects.

'''分子流行病学molecular epidemiology'''中研究的现象是在'''分子生物学'''水平上的，也涵盖了遗传学。而遗传学中的'''生物标志物biomarkers'''就是原因或结果的证据。

A recent trend{{when|date=August 2014}} is to identify [[evidence]] for influence of the exposure on [[molecular pathology]] within diseased [[Tissue (biology)|tissue]] or cells, in the emerging interdisciplinary field of [[molecular pathological epidemiology]] (MPE).{{third-party-inline|date=August 2014}} Linking the exposure to molecular pathologic signatures of the disease can help to assess causality. {{third-party-inline|date=August 2014}} Considering the inherent nature of [[heterogeneity]] of a given disease, the unique disease principle, disease phenotyping and subtyping are trends in biomedical and [[public health]] sciences, exemplified as [[personalized medicine]] and [[precision medicine]].{{third-party-inline|date=August 2014}}

在新兴的'''分子病理流行病学molecular pathological epidemiology (MPE)'''交叉学科领域，最近的一个趋势（截至2014年）是确定在病变组织或细胞内，'''暴露exposure '''在'''分子病理学molecular pathology'''上的影响。将暴露与疾病的分子病理特征联系起来可以帮助因果关系的评估。鉴于给定疾病的'''异质性'''的固有特征、独特的疾病原理等，疾病'''表现型phenotyping'''和'''亚型subtyping '''现在是生物医学和'''公共卫生科学public health'''的趋势，例证包括'''个体化医学personalized medicine'''和'''精准医学precision medicine'''等。

==In computer science在计算机科学领域==

Determination of cause and effect from joint observational data for two time-independent variables, say X and Y, has been tackled using asymmetry between evidence for some model in the directions, X → Y and Y → X. The primary approaches are based on [[Algorithmic information theory]] models and noise models.{{Citation needed|date=May 2019}}

确定两个时间独立变量：X 和 Y 的联合观测数据因果关系的问题已经被解决了，方法是利用 X → Y 和 Y → X 方向上某些模型的证据不对称性。主要的方法基于'''算法信息理论Algorithmic information theory'''模型和'''噪声模型noise models'''。

===Algorithmic information models算法信息模型===

Compare two programs, both of which output both X and Y.

比较两个同时输出 X 和 Y 的程序。
* Store Y and a compressed form of X in terms of uncompressed Y.

* Store X and a compressed form of Y in terms of uncompressed X.

* 用未压缩的 X 来存储 X 和压缩形式的 Y 。

The shortest such program implies the uncompressed stored variable more-likely causes the computed variable.<ref>Kailash Budhathoki and Jilles Vreeken "[http://eda.mmci.uni-saarland.de/pubs/2016/origo-budhathoki,vreeken.pdf Causal Inference by Compression]" 2016 IEEE 16th International Conference on Data Mining (ICDM)</ref><ref>{{Cite journal |doi = 10.1007/s10115-018-1286-7|title = Telling cause from effect by local and global regression|journal = Knowledge and Information Systems|year = 2018|last1 = Marx|first1 = Alexander|last2 = Vreeken|first2 = Jilles|volume=60|issue = 3|pages=1277–1305|doi-access = free}}</ref>

最短的这种程序意味着，更有可能是未压缩的'''存储变量stored variable'''导致了'''计算出的变量computed variable'''。

===Noise models噪音模型===

Incorporate an independent noise term in the model to compare the evidences of the two directions.

在模型中引入一个独立的噪声项，以比较两个方向的证据。

Here are some of the noise models for the hypothesis Y → X with the noise E:

下面是一些支持 Y → X 假设且具有噪声 E 的噪声模型:
* Additive noise:<ref>Hoyer, Patrik O., et al. "[https://papers.nips.cc/paper/3548-nonlinear-causal-discovery-with-additive-noise-models.pdf Nonlinear causal discovery with additive noise models]." NIPS. Vol. 21. 2008.</ref> <math>Y = F(X)+E</math>
* '''加法噪音Additive noise'''

* Linear noise:<ref>{{cite journal | last1 = Shimizu | first1 = Shohei | display-authors = etal | year = 2011 | title = DirectLiNGAM: A direct method for learning a linear non-Gaussian structural equation model | url = http://www.jmlr.org/papers/volume12/shimizu11a/shimizu11a.pdf | journal = The Journal of Machine Learning Research | volume = 12 | issue = | pages = 1225–1248 }}</ref> <math>Y = pX + qE</math>
* '''线性噪音Linear noise'''

* Post-non-linear:<ref>Zhang, Kun, and Aapo Hyvärinen. "[https://arxiv.org/pdf/1205.2599 On the identifiability of the post-nonlinear causal model]." Proceedings of the Twenty-Fifth Conference on Uncertainty in Artificial Intelligence. AUAI Press, 2009.</ref> <math>Y = G(F(X)+E)</math>
* '''后非线性Post-non-linear（噪音）'''

* Heteroskedastic noise: <math>Y = F(X)+E.G(X)</math>
* '''异方差噪音Heteroskedastic noise'''

* Functional noise:<ref name="Mooij">Mooij, Joris M., et al. "[http://papers.nips.cc/paper/4173-probabilistic-latent-variable-models-for-distinguishing-between-cause-and-effect.pdf Probabilistic latent variable models for distinguishing between cause and effect]." NIPS. 2010.</ref> <math>Y = F(X,E)</math>
* '''功能性噪音Functional noise'''

The common assumption in these models are:

这些模型的共同假设是:
* There are no other causes of Y.
* Y 没有其他原因。

* X and E have no common causes.
* X 和 E 没有共同的原因。

* Distribution of cause is independent from causal mechanisms.
* 原因的分布独立于因果机制。

On an intuitive level, the idea is that the factorization of the joint distribution P(Cause, Effect) into P(Cause)*P(Effect | Cause) typically yields models of lower total complexity than the factorization into P(Effect)*P(Cause | Effect). Although the notion of “complexity” is intuitively appealing, it is not obvious how it should be precisely defined.<ref name="Mooij"/> A different family of methods attempt to discover causal "footprints" from large amounts of labeled data, and allow the prediction of more flexible causal relations.<ref>Lopez-Paz, David, et al. "[http://www.jmlr.org/proceedings/papers/v37/lopez-paz15.pdf Towards a learning theory of cause-effect inference]" ICML. 2015</ref>

在直观的层面上，这个想法是联合分布P(Cause, Effect) 到 P(Cause)*P(Effect | Cause)的因式分解通常产生的模型的总'''复杂性complexity '''低于到P(Effect)*P(Cause | Effect)的因式分解。尽管“复杂性”的概念在直觉上很吸引人，但是对于如何定义它却并不显而易见。另一种不同类族的方法尝试从大量标签过的数据中发现因果的“足迹”，并且允许预测更灵活的因果关系。

== In statistics and economics 在统计学和经济学领域==

{{Main|Causality#Statistics and economics}}

--[[用户:嘉树|嘉树]]（[[用户讨论:嘉树|讨论]]）本段似有错漏，英文词条和本段内容有一些不同。因此，（1）先写本段的翻译，（2）再写英文词条中有不同的地方，（3）最后整合一下。【】括起来的是在两个版本中需要照应和修改的部分。

In [[statistics]] and [[economics]], causality is often tested via [[regression analysis]]. Several methods can be used to distinguish actual causality from spurious correlations. First, economists constructing regression models establish the direction of causal relation based on economic theory (theory-driven econometrics). For example, if one studies the dependency between rainfall and the future price of a commodity, then theory (broadly construed) indicates that rainfall can influence prices, but futures prices cannot make changes to the amount of rain<ref>{{Cite book|last=Simon|first=Herbert|title=Models of Discovery|publisher=Springer|year=1977|location=Dordrecht|page=52}}</ref> . Second, the [[instrumental variables]] (IV) technique may be employed to remove any reverse causation by introducing a role for other variables (instruments) that are known to be unaffected by the dependent variable. Third, economists consider time precedence to choose appropriate model specification. Given that partial correlations are symmetrical, one cannot determine the direction of causal relation based on correlations only. Based on the notion of probabilistic view on causality, economists assume that causes must be prior in time than their effects. This leads to using the variables representing phenomena happening earlier as independent variables and developing econometric tests for causality (e.g., Granger-causality tests) applicable in time series analysis<ref>{{Cite book|last=Maziarz|first=Mariusz|title=The Philosophy of Causality in Economics: Causal Inferences and Policy Proposals|publisher=Routledge|year=2020|location=New York}}</ref>. Fifth, other regressors are included to ensure that [[confounding variable]]s are not causing a regressor to appear to be significant spuriously but, in the areas suffering from the problem of multicollinearity such as macroeconomics, it is in principle impossible to include all confounding factors and therefore econometric models are susceptible to the common-cause fallacy.<ref>{{Cite journal|last=Henschen|first=Tobias|date=2018|title=The in-principle inconclusiveness of causal evidence in macroeconomics|journal=European Journal for Philosophy of Science|volume=8|pages=709–733}}</ref>. Recently, the movement of design-based econometrics has popularized using natural experiments and quasi-experimental research designs to address the problem of spurious correlations.<ref>{{Cite book|last=Angrist Joshua & Pischke Jörn-Steffen|title=Mostly Harmless Econometrics: An Empiricist's Companion|publisher=Princeton University Press|year=2008|location=Princeton}}</ref>

在统计学和经济学中，因果关系通常通过回归分析来检验。有几种方法可以用来区分真实的因果关系和虚假的相关性。第一，经济学家根据经济理论('''理论驱动theory-driven'''的计量经济学)构建回归模型，从而确定因果关系的方向。
例如，如果研究降雨与未来商品价格之间的依赖关系，那么一个广义上建构的理论表明，降雨可以影响价格，但未来价格不能改变降雨量。<ref>{{Cite book|last=Simon|first=Herbert|title=Models of Discovery|publisher=Springer|year=1977|location=Dordrecht|page=52}}</ref> . 第二，'''工具变量instrumental variables(IV)'''技术可以通过引入其他已知不受因变量的影响的工具变量来消除任何反向因果关系。【第三，经济学家会考虑时间优先级来选择合适的具体模型。由于'''偏相关partial correlations'''是对称的，人们不能在相关的基础上确定因果关系的方向。经济学家基于因果关系的'''概率观点probabilistic view'''假设，原因必须在时间上优先于其结果。这导致经济学家使用较早发生的现象作为自变量，并开发适用于时间序列分析的因果关系检验计量经济方法（例如，'''格兰杰因果检验'''）<ref>{{Cite book|last=Maziarz|first=Mariusz|title=The Philosophy of Causality in Economics: Causal Inferences and Policy Proposals|publisher=Routledge|year=2020|location=New York}}</ref>。第五，有些做法包括了其他回归项，从而确保'''混淆变量confounding variables'''不会导致某个回归因素显得明显虚假，但遭受'''多重共线性multicollinearity'''问题困扰的领域，如宏观经济学，原则上不可能包括所有混淆因素，因此计量经济模型容易出现'''共因谬误common-cause fallacy'''<ref>{{Cite journal|last=Henschen|first=Tobias|date=2018|title=The in-principle inconclusiveness of causal evidence in macroeconomics|journal=European Journal for Philosophy of Science|volume=8|pages=709–733}}</ref>。近年来，'''以研究设计为基础的计量经济学design-based econometrics'''运动已经推广使用自然实验和准实验研究设计来解决'''虚假相关spurious correlations'''的问题<ref>{{Cite book|last=Angrist Joshua & Pischke Jörn-Steffen|title=Mostly Harmless Econometrics: An Empiricist's Companion|publisher=Princeton University Press|year=2008|location=Princeton}}</ref>。】

--[[用户:嘉树|嘉树]]（[[用户讨论:嘉树|讨论]]）英文词条的第三和第四：

Third, the principle that effects cannot precede causes can be invoked, by including on the right side of the regression only variables that precede in time the dependent variable.
Fourth, other regressors are included to ensure that confounding variables are not causing a regressor to spuriously appear to be significant. Correlation by coincidence, as opposed to correlation reflecting actual dependence of the underlying process, can be ruled out by using large samples and by performing cross validation to check that correlations are maintained on data that were not used in the regression.

【第三，通过在回归的右侧只包括时间上在因变量之前的变量，就可以使用结果不能优先于原因的原则。
第四，有些方法包括了其他回归因素，以确保'''混淆变量confounding variables'''不会导致一个回归项虚假地呈现显著。通过使用大样本和交叉验证检查在回归中未使用的数据上是否保持了相关性，可以排除巧合的，而不是反映实际依赖内在过程的相关性。】

--[[用户:嘉树|嘉树]]（[[用户讨论:嘉树|讨论]]）整合后的翻译：

在统计学和经济学中，因果关系通常通过回归分析来检验。有几种方法可以用来区分真实的因果关系和虚假的相关性。第一，经济学家根据经济理论('''理论驱动theory-driven'''的计量经济学)构建回归模型，从而确定因果关系的方向。例如，如果研究降雨与未来商品价格之间的依赖关系，那么一个广义上建构的理论表明，降雨可以影响价格，但未来价格不能改变降雨量。<ref>{{Cite book|last=Simon|first=Herbert|title=Models of Discovery|publisher=Springer|year=1977|location=Dordrecht|page=52}}</ref> . 第二，'''工具变量instrumental variables(IV)'''技术可以通过引入其他已知不受因变量的影响的工具变量来消除任何反向因果关系。第三，通过在回归的右侧只包括时间上在因变量之前的变量，就可以使用结果不能优先于原因的原则。由于'''偏相关partial correlations'''是对称的，人们不能在相关的基础上确定因果关系的方向。经济学家基于因果关系的'''概率观点probabilistic view'''假设，原因必须在时间上优先于其结果。这导致经济学家使用较早发生的现象作为自变量，并开发适用于时间序列分析的因果关系检验计量经济方法（例如，'''格兰杰因果检验'''）<ref>{{Cite book|last=Maziarz|first=Mariusz|title=The Philosophy of Causality in Economics: Causal Inferences and Policy Proposals|publisher=Routledge|year=2020|location=New York}}</ref>。第四，有些方法包括了其他回归因素，以确保'''混淆变量confounding variables'''不会导致一个回归项虚假地呈现显著。通过使用大样本和交叉验证检查在回归中未使用的数据上是否保持了相关性，可以排除巧合的，而不是反映实际依赖内在过程的相关性。但遭受'''多重共线性multicollinearity'''问题困扰的领域，如宏观经济学，原则上不可能包括所有混淆因素，因此计量经济模型容易出现'''共因谬误common-cause fallacy'''<ref>{{Cite journal|last=Henschen|first=Tobias|date=2018|title=The in-principle inconclusiveness of causal evidence in macroeconomics|journal=European Journal for Philosophy of Science|volume=8|pages=709–733}}</ref>。近年来，'''以研究设计为基础的计量经济学design-based econometrics'''运动已经推广使用自然实验和准实验研究设计来解决'''虚假相关spurious correlations'''的问题<ref>{{Cite book|last=Angrist Joshua & Pischke Jörn-Steffen|title=Mostly Harmless Econometrics: An Empiricist's Companion|publisher=Princeton University Press|year=2008|location=Princeton}}</ref>。

== In social science 在社会科学领域==

The social sciences have moved increasingly toward a quantitative framework for assessing causality. Much of this has been described as a means of providing greater rigor to social science methodology. Political science was significantly influenced by the publication of [[Designing Social Inquiry]], by Gary King, Robert Keohane, and Sidney Verba, in 1994. King, Keohane, and Verba (often abbreviated as KKV) recommended that researchers applying both quantitative and qualitative methods adopt the language of statistical inference to be clearer about their subjects of interest and units of analysis.<ref>{{Cite book|title=Designing social inquiry : scientific inference in qualitative research|first=Gary|last=King|date=2012|publisher=Princeton Univ. Press|isbn=978-0691034713|oclc=754613241}}</ref><ref name=":0">{{Cite journal|last=Mahoney|first=James|date=January 2010|title=After KKV|journal=World Politics|volume=62|issue=1|pages=120–147|jstor=40646193|doi=10.1017/S0043887109990220}}</ref> Proponents of quantitative methods have also increasingly adopted the [[Rubin causal model|potential outcomes framework]], developed by [[Donald Rubin]], as a standard for inferring causality.{{Citation needed|date=May 2019}}

社会科学越来越倾向评估因果关系的定量框架。框架中的很大一部分已经被描述为一种提供更严格的'''社会科学方法social science methodology'''的方式。1994年，'''加里·金Gary King'''、'''罗伯特 · 基奥汉Robert Keohane'''和'''西德尼 · 维尔巴Sidney Verba'''合著的《'''设计社会学问卷Designing Social Inquiry'''》对政治科学产生了重大影响。'''金、基奥汉，和维尔巴（通常缩写为 KKV）建议研究人员同时采用定量和定性的方法，采用统计推论的语言来更清楚地说明他们感兴趣的主题和分析的单位。King, Keohane, and Verba (often abbreviated as KKV) recommended that researchers applying both quantitative and qualitative methods adopt the language of statistical inference to be clearer about their subjects of interest and units of analysis.'''<ref>{{Cite book|title=Designing social inquiry : scientific inference in qualitative research|first=Gary|last=King|date=2012|publisher=Princeton Univ. Press|isbn=978-0691034713|oclc=754613241}}</ref><ref name=":0">{{Cite journal|last=Mahoney|first=James|date=January 2010|title=After KKV|journal=World Politics|volume=62|issue=1|pages=120–147|jstor=40646193|doi=10.1017/S0043887109990220}}</ref>定量方法的支持者也越来越多地采用'''唐纳德 · 鲁宾Donald Rubin'''开发的'''潜在结果框架potential outcomes framework'''作为推断因果关系的标准。
Debates over the appropriate application of quantitative methods to infer causality resulted in increased attention to the reproducibility of studies. Critics of widely-practiced methodologies argued that researchers have engaged in [[Data dredging|P hacking]] to publish articles on the basis of spurious correlations.<ref>{{Cite news|url=https://www.nytimes.com/2017/10/18/magazine/when-the-revolution-came-for-amy-cuddy.html|title=When the Revolution Came for Amy Cuddy|last=Dominus|first=Susan|date=18 October 2017|work=The New York Times|access-date=2019-03-02|language=en-US|issn=0362-4331}}</ref> To prevent this, some have advocated that researchers preregister their research designs prior to conducting to their studies so that they do not inadvertently overemphasize a non-reproducible finding that was not the initial subject of inquiry but was found to be statistically significant during data analysis.<ref>{{Cite web|url=https://www.americanscientist.org/article/the-statistical-crisis-in-science|title=The Statistical Crisis in Science|date=6 February 2017|website=American Scientist|language=en|access-date=2019-04-18}}</ref> Internal debates about methodology and reproducibility within the social sciences have at times been acrimonious.{{Citation needed|date=May 2019}}

合适地应用定量方法来推断因果关系的相关争论导致了对研究'''可重复性reproducibility'''的更多关注。对广泛被使用的方法持批评态度的人认为，研究人员利用'''数据挖掘Data dredging'''或'''p-hacking'''技术以在虚假相关的基础上发表文章<ref>{{Cite news|url=https://www.nytimes.com/2017/10/18/magazine/when-the-revolution-came-for-amy-cuddy.html|title=When the Revolution Came for Amy Cuddy|last=Dominus|first=Susan|date=18 October 2017|work=The New York Times|access-date=2019-03-02|language=en-US|issn=0362-4331}}</ref>。为了避免这种情况的发生，一些人主张研究人员在进行研究之前'''预注册preregister'''他们的研究设计，这样他们就不会无意中过分强调一项不可复制的发现，这项发现并非最初的调查对象，但在数据分析中被发现具有统计意义<ref>{{Cite web|url=https://www.americanscientist.org/article/the-statistical-crisis-in-science|title=The Statistical Crisis in Science|date=6 February 2017|website=American Scientist|language=en|access-date=2019-04-18}}</ref>。社会科学内部关于方法论和可重复性的争论有时是尖锐的{{Citation needed|date=May 2019}}。

While much of the emphasis remains on statistical inference in the potential outcomes framework, social science methodologists have developed new tools to conduct causal inference with both qualitative and quantitative methods, sometimes called a “mixed methods” approach.<ref>{{Cite book|url=https://books.google.com/books/about/Designing_and_Conducting_Mixed_Methods_R.html?id=YcdlPWPJRBcC|title=Designing and Conducting Mixed Methods Research|last=Creswell|first=John W.|last2=Clark|first2=Vicki L. Plano|date=2011|publisher=SAGE Publications|isbn=9781412975179|language=en}}</ref><ref>{{Cite book|url=https://www.cambridge.org/core/books/multimethod-social-science/286C2742878FBCC6225E2F10D6095A0C|title=Multi-Method Social Science by Jason Seawright|last=Seawright|first=Jason|date=September 2016|website=Cambridge Core|language=en|access-date=2019-04-18|doi=10.1017/CBO9781316160831|isbn=9781316160831}}</ref> Advocates of diverse methodological approaches argue that different methodologies are better suited to different subjects of study. Sociologist Herbert Smith and Political Scientists James Mahoney and Gary Goertz have cited the observation of Paul Holland, a statistician and author of the 1986 article “Statistics and Causal Inference,” that statistical inference is most appropriate for assessing the “effects of causes” rather than the “causes of effects.”<ref>{{Cite journal|last=Smith|first=Herbert L.|date=10 February 2014|title=Effects of Causes and Causes of Effects: Some Remarks from the Sociological Side|journal=Sociological Methods and Research|volume=43|issue=3|pages=406–415|doi=10.1177/0049124114521149|pmid=25477697|pmc=4251584}}</ref><ref>{{Cite journal|last=Goertz|first=Gary|last2=Mahoney|first2=James|date=2006|title=A Tale of Two Cultures: Contrasting Quantitative and Qualitative Research|journal=Political Analysis|language=en|volume=14|issue=3|pages=227–249|doi=10.1093/pan/mpj017|issn=1047-1987}}</ref> Qualitative methodologists have argued that formalized models of causation, including process tracing and fuzzy set theory, provide opportunities to infer causation through the identification of critical factors within case studies or through a process of comparison among several case studies.<ref name=":0" /> These methodologies are also valuable for subjects in which a limited number of potential observations or the presence of confounding variables would limit the applicability of statistical inference.{{Citation needed|date=May 2019}}

虽然在潜在结果框架中大部分重点仍然放在统计推论上，但社会科学方法学家已经开发出新的定性和定量方法来进行因果推断，有时被称为'''混合方法mixed methods'''。多种不同方法的支持者认为它更适合'''不同学科的研究different subjects of study'''。
--[[用户:嘉树|嘉树]]（[[用户讨论:嘉树|讨论]]）学科还是对象？
社会学家 Herbert Smith 和政治学家 James Mahoney 、 Gary Goertz 引用了统计学家 Paul Holland 的观察结果，Paul Holland在1986年发表了一篇名为《'''统计学和因果推断Statistics and Causal Inference'''》的文章，认为推论统计学最适合于评估“结果的原因”而不是“结果的原因”。定性方法学家认为，形式化的因果关系模型，包括'''过程追踪process tracing'''和'''模糊集理论fuzzy set theory'''，通过在某个案例研究内识别关键因素或在几个案例研究之间比较的过程提供了推断因果关系的机会。这些方法对于那些可能的观察数量有限或存在混淆变量从而限制统计推论适用性的课题也是有价值的。

== See also ==

参见
* [[Causal analysis]] 因果分析

* [[Granger causality]] 格兰杰因果分析

* [[Multivariate statistics]] 多元统计

* [[Partial least squares regression]] 偏最小二乘回归

* [[Pathogenesis]] 发病学

* [[Pathology]] 病理学

* [[Regression analysis]] 回归分析

* [[Transfer entropy]] 传递熵

== References ==

参考资料
{{Reflist}}

==Bibliography==

参考书目
* {{cite book |ref=what_if |last1=Hernán |first1=MA |author-link1=Miguel Hernán |last2=Robins |first2=JM |author-link2=James Robins |title=Causal Inference: What If |location=Barnsley |publisher=Boca Raton: Chapman & Hall/CRC |date=2020-01-21|url=https://www.hsph.harvard.edu/miguel-hernan/causal-inference-book/}}

==External links==

外部链接
{{Commons category}}

*[http://clopinet.com/isabelle/Projects/NIPS2013/ NIPS 2013 Workshop on Causality]

*[http://webdav.tuebingen.mpg.de/causality/ Causal inference at the Max-Planck-Institute for Intelligent Systems Tübingen]

{{Portal bar|Science}}

{{Use dmy dates|date=October 2019}}

== 编者推荐 ==
===集智课程推荐===
[https://campus.swarma.org/course/1078 社交网络中的因果推断] 本课程中，将简要介绍一些基本的因果推断策略，并聚焦社会网络分析中的因果推断问题，涉及社会网络实验设计、固定样本、工具变量和敏感度分析等。

===书籍推荐===
[https://book.douban.com/subject/33438811/ 为什么:关于因果关系的新科学] 在本书中，人工智能领域的权威专家Judea Pearl及其同事领导的因果关系革命突破多年的迷雾，厘清了知识的本质，确立了因果关系研究在科学探索中的核心地位。

[[Category:Causal inference| ]]

[[Category:Graphical models]]

类别: 图形模型
[[Category:Regression analysis]]

类别: 回归分析
[[Category:Inductive reasoning]]

类别: 归纳推理
[[Category:Philosophy of statistics]]

分类: 统计哲学
<noinclude>

This page was moved from [[wikipedia:en:Causal inference]]. Its edit history can be viewed at [[因果推断/edithistory]]</noinclude><noinclude>

This page was moved from [[mywiki:zh-cn:因果推断]]. Its edit history can be viewed at [[因果推断/edithistory]]</noinclude>