Likelihood Ratio Tests for Multiply Imputed Datasets: Introducing milrtest
Likelihood Ratio Tests for Multiply Imputed Datasets: Introducing milrtest
复制标题
多重插补数据集的似然比检验：milrtest 简介
DOI：
--
复制
发表时间：
2008
期刊：
影响因子：
--
通讯作者：
R. Medeiros
中科院分区：
文献类型：
--
作者：
R. Medeiros
通过使用用户编写的程序，主要是mim（Carlin，加拉蒂和Royston，2008），Stata用户可以分析多重插补（MI）数据集。在其他功能中，mim允许用户估计一系列回归模型，并在使用Wald检验进行模型估计后执行多参数假设检验。这里介绍的程序允许用户使用mim后的多重插补数据集对模型进行似然比检验。这提供了在使用MI数据估计后测试嵌套模型的额外方法。Meng和Rubin（1992）描述了用于执行似然比检验的过程。基于两组似然比检验计算检验统计量。第一个涉及计算m个插补数据集中每个数据集的零假设与备择假设的似然比。第二种方法涉及计算m个数据集中每个数据集中的零假设和备择假设的似然性，基于m个数据集的组合系数估计值（即m个插补数据集的参数估计值的平均值）将参数约束为估计值。当前版本允许测试有限数量的回归命令（即回归，logit和ologit），但后续版本可能包括与其他命令的兼容性。
Through the use of user-written programs, primarily mim (Carlin, Galati, and Royston, 2008), Stata users can analyze multiply imputed (MI) datasets. Among other capabilities, mim allows the user to estimate a range of regression models and to perform a multi-parameter hypothesis tests after model estimation using a Wald test. The program presented here allows the user to perform likelihood ratio tests on models using multiply imputed datasets after mim. This provides an additional means of testing nested models after estimation using MI data. The process used to perform the likelihood ratio tests is described in Meng and Rubin (1992). The test statistic is calculated based on two sets of likelihood ratio tests. The first involves calculating the likelihood ratio for the null versus alternative hypothesis in each of the m imputed datasets. The second involves calculating the likelihood for the null and alternative hypotheses in each of the m datasets, constraining the parameters to be the estimates based on combining coefficient estimates from the m datasets (i.e. the average of the parameter estimates across the m imputed datasets). The current version allows testing for a limited number of regression commands (i.e. regression, logit, and ologit), but subsequent versions may include compatibility with additional commands.