https://wiki.swarma.org/api.php?action=feedcontributions&feedformat=atom&user=1587causalai 2026-11-02T18:38:45Z 用户贡献 MediaWiki 1.35.0 https://wiki.swarma.org/index.php?title=%E5%9B%A0%E6%9E%9C%E6%A3%AE%E6%9E%97_Causal_Forest&diff=32878 2022-07-07T14:33:28Z

<p>1587causalai：quick start</p> <hr /> <div>因果森林 (Causal Forest) 是由 Wager and Athey [2017] 提出的异质因果效应估计算法。该算法本质上可以理解成通过子采样生成大量不同的因果树，然后取这些树的平均。 类似于随机森林算法，因果森林可以被理解成一种近邻匹配算法，但是用数据驱动的方法来确定样本之间的相似度。 <br /> <br /> == 介绍 ==<br /> <br /> <br /> 待补充<br /> <br /> <br /> $$\hat{\theta}(x) = \argmin_{\theta} \sum_{i=1}^n K_x(X_i)\cdot \left( Y_i - \hat{q}(X_i, W_i) - \theta \cdot (T_i - \hat{f}(X_i, W_i)) \right)^2$$<br /> <br /> ==算法==<br /> <br /> [[文件:广义随机森林.png|缩略图]]<br /> 待补充<br /> ....<br /> <br /> ==算法实现==<br /> <br /> <br /> Python 包 econml 和 R 包 grf 都有实现该算法。<br /> <br /> ==参考文献==<br /> <br /> <br /> ===Recursive Partitioning for Heterogeneous Causal Effects - arXiv===<br /> ''[Submitted on 5 Apr 2015 (v1), last revised 30 Dec 2015 (this version, v3)]''<br /> <br /> ===Estimation and Inference of Heterogeneous Treatment Effects ... ===<br /> ''[Submitted on 14 Oct 2015 (v1), last revised 10 Jul 2017 (this version, v4)]''<br /> <br /> ===Generalized Random Forests - arXiv===<br /> ''[Submitted on 5 Oct 2016 (v1), last revised 5 Apr 2018 (this version, v4)]''<br /> <br /> ===Machine Learning Methods Economists Should Know About===<br /> ''[Submitted on 24 Mar 2019]''<br /> <br /> ==编者推荐==<br /> <br /> <br /> 待补充</div>

1587causalai https://wiki.swarma.org/index.php?title=%E6%96%87%E4%BB%B6:%E5%B9%BF%E4%B9%89%E9%9A%8F%E6%9C%BA%E6%A3%AE%E6%9E%97.png&diff=32877 2022-07-07T14:32:06Z

<p>1587causalai：</p> <hr /> <div>测试</div>

1587causalai https://wiki.swarma.org/index.php?title=%E5%9B%A0%E6%9E%9C%E6%A3%AE%E6%9E%97_Causal_Forest&diff=32876 2022-07-07T14:27:27Z

<p>1587causalai：快速撰写</p> <hr /> <div>因果森林 (Causal Forest) 是由 Wager and Athey [2017] 提出的异质因果效应估计算法。该算法本质上可以理解成通过子采样生成大量不同的因果树，然后取这些树的平均。 类似于随机森林算法，因果森林可以被理解成一种近邻匹配算法，但是用数据驱动的方法来确定样本之间的相似度。 <br /> <br /> == 介绍 ==<br /> <br /> <br /> <br /> == 算法 ==<br /> <br /> <br /> ....<br /> <br /> == 算法实现 ==<br /> <br /> <br /> Python 包 econml 和 R 包 grf 都有实现该算法。<br /> <br /> == 参考文献 ==<br /> <br /> <br /> === Recursive Partitioning for Heterogeneous Causal Effects - arXiv ===<br /> ''[Submitted on 5 Apr 2015 (v1), last revised 30 Dec 2015 (this version, v3)]''<br /> <br /> === Estimation and Inference of Heterogeneous Treatment Effects ... ===<br /> ''[Submitted on 14 Oct 2015 (v1), last revised 10 Jul 2017 (this version, v4)]''<br /> <br /> === Generalized Random Forests - arXiv ===<br /> ''[Submitted on 5 Oct 2016 (v1), last revised 5 Apr 2018 (this version, v4)]''<br /> <br /> === Machine Learning Methods Economists Should Know About ===<br /> ''[Submitted on 24 Mar 2019]''<br /> <br /> == 编者推荐 ==</div>

1587causalai https://wiki.swarma.org/index.php?title=%E5%9B%A0%E6%9E%9C%E6%A3%AE%E6%9E%97_Causal_Forest&diff=32873 2022-07-07T13:48:46Z

<p>1587causalai：因果森林(Causal Forest) 是由Susan Athey、Stefan Wager 于 2015 提出的估计异质处理效应的随机森林算法。</p> <hr /> <div></div>

1587causalai