Multiple imputation of covariates by substantive-model compatible fully conditional specification
Multiple imputation of covariates by substantive-model compatible fully conditional specification
复制标题
DOI：
10.1177/1536867x1501500206
复制
发表时间：
2015-01-01
期刊：
影响因子：
4.8
通讯作者：
Morris, Tim P.
中科院分区：
文献类型：
--
作者：
Bartlett, Jonathan W.;Morris, Tim P.
多重插补是处理缺失数据的一种实用的原则性方法。当用于插补回归模型协变量中的缺失值时，如果插补模型与结局的实质性关注模型不兼容，则可能会错误指定插补模型。在这篇文章中，我们介绍了smcf cs命令，它通过实质模型兼容的完全条件规范来估算协变量。这修改了流行的完全条件规范或链式方程的方法，通过将每个协变量与用户指定的实质性模型兼容地插补到多重插补。我们比较smcf cs命令与标准的完全条件规范插补，在模拟研究中使用mi插补链，并对来自乳腺癌肿瘤复发时间研究的数据进行说明性分析。
Multiple imputation is a practical, principled approach to handling missing data. When used to impute missing values in covariates of regression models, imputation models may be misspecified if they are not compatible with the substantive model of interest for the outcome. In this article, we introduce the smcf cs command, which imputes covariates by substantive-model compatible fully conditional specification. This modifies the popular fully conditional specification or chained-equations approach to multiple imputation by imputing each covariate compatibly with a user-specified substantive model. We compare the smcf cs command with standard fully conditional specification imputation using mi impute chained in a simulation study and illustrative analysis of data from a study investigating time to tumor recurrence in breast cancer.