更改

分层随机试验 (查看源代码)

2021年6月9日 (三) 11:20的版本

删除3,086字节、 2021年6月9日 (三) 11:20

→‎分层随机试验的步骤

第11行：第11行：

# 定义目标总体

−

+

#定义分层 '''变量 Variables''' 并决定要创建的分层数量。确定分层变量的标准,包括年龄、社会经济地位、国籍、种族、教育程度等，并应与研究目标相一致。理想情况下，应该使用4-6个阶层，因为任何分层变量的增加将提高其中一些变量抵消其他变量的影响的概率。<ref name=":5" />

−

# Define stratification [[Variable and attribute (research)|variables]] and decide the number of strata to be created. The criteria for defining variables for stratification include [[Ageing|age]], [[socioeconomic status]], [[nationality]], [[Race (human categorization)|race]], [[Educational stage|education level]] and others and should be in line with the research objective. Ideally, the number of 4-6strata should be employed, as any increase in stratification variables will raise the probability for some of them to cancel out the impact of other variables.<ref name=":5" />

−

Define stratification variables and decide the number of strata to be created. The criteria for defining variables for stratification include age, socioeconomic status, nationality, race, education level and others and should be in line with the research objective. Ideally, the number of 4-6strata should be employed, as any increase in stratification variables will raise the probability for some of them to cancel out the impact of other variables.

−

定义分层 '''变量 Variables''' 并决定要创建的分层数量。确定分层变量的标准,包括年龄、社会经济地位、国籍、种族、教育程度等，并应与研究目标相一致。理想情况下，应该使用4-6个阶层，因为任何分层变量的增加将提高其中一些变量抵消其他变量的影响的概率。<ref name=":5" />

−

~~# Use a [[sampling frame]] to evaluate all the elements in the target population. Make changes afterwards based on [[Coverage probability|coverage]] and grouping.~~

−

#使用 '''抽样框架 Sampling frame''' 评估目标总体中的所有元素。之后根据 '''覆盖率 Coverage''' 和分组进行更改。

−

# List all the elements and consider the sampling result. Each stratum should be [[Mutual exclusivity|mutually exclusive]] and add up to cover all members of the population, whilst each member of the population should fall into [[Uniqueness quantification|unique]] stratum, along with other members with minimum differences.<ref name=":4" />

#列出所有的元素并考虑抽样结果。每个阶层应该相互排斥 Mutually exclusive，加起来涵盖总体的所有成员，而总体的每一个成员应该

属于唯一的阶层，和其他差异最小的成员一起。<ref name=":4" />

−

The number of subgroups can be calculated by multiplying the number of strata for each factor. Factors are measured before or at the time of randomization and experimental subjects are divided into several subgroups or strata according to the results of measurements.

−

~~！！！子群的数目可以用每个因素的阶层数目相乘来计算。因子在随机化之前或之时被测量，实验对象根据测量结果被分成若干子群或阶层。~~

−

~~# Make decisions over the random sampling selection criteria. This can be done manually or with a designed computer program.~~

−

#决定随机抽样的选择标准。这可以手动完成，也可以用设计好的计算机程序完成。

−

~~# Assign a random and unique number to all the elements followed by sorting these elements according to their number assigned.~~

#为所有元素分配一个随机且唯一的编号，然后根据分配的编号对这些元素进行排序。

−

~~Within each stratum, several randomization strategies can be applied, which involves simple randomization, blocked randomization, and minimization.~~

−

~~！！！！在每个地层中，可以采用多种随机化策略，包括简单的随机化、阻塞随机化和最小化。~~

−

# Review the size of each stratum and [[Probability distribution|numerical distribution]] of all elements in every strata. Determine the type of sampling, either proportional or disproportional stratified sampling.

#回顾每一层的大小（Size）和每一层中所有元素的 '''数值分布 Numerical distribution''' 。确定抽样类型，按比例或不按比例分层抽样。

−

# Carry out the selected random sampling as defined in step 5. At minimum, one element must be chosen from each stratum so that the final sample includes representatives from every stratum. If two or more elements from each stratum are selected, [[Margin of error|error margins]] of the collected data can be calculated.<ref name=":5" />

−

#按照第5步中的规定进行所选的随机抽样。至少，必须从每个阶层中选择一种元素，以便最终样品包括每个阶层的代表。如果从每个阶层中选择两个或两个以上的元素，则可以计算所收集数据的 '''误差范围 Error margins''' 。

+

Simple randomization is considered as the easiest method for allocating subjects in each stratum. Subjects are assigned to each group purely randomly for every assignment. Even though it is easy to conduct, simple randomization is commonly applied in strata that contain more than 100 samples since a small sampling size would make assignment unequal.

孙钦贵

387

个编辑