Multiple imputation in multivariate problems when the imputation and analysis models differ

Multiple imputation in multivariate problems when the imputation and analysis models differ
复制标题

DOI:
10.1111/1467-9574.00218
复制
发表时间:
2003-02-01
影响因子:
1.5
通讯作者:
Schafer, JL
Schafer, JL
中科院分区:
数学4区
文献类型:
--
作者:
Schafer, JL

文献摘要

被引文献

相似文献

贝叶斯多重归罪(MI)已成为在许多情况下处理缺失值的一种非常有用的范例。在本文中,我将贝叶斯MI与其他方法--特别是最大似然法--进行了比较,并指出了它的一些独特特征。MI的一个关键方面,即归罪阶段与分析阶段的分离,在两个阶段背后的模型不一致的情况下可能是有利的。
Bayesian multiple imputation (MI) has become a highly useful paradigm for handling missing values in many settings. In this paper, I compare Bayesian MI with other methods - maximum likelihood, in particular-and point out some of its unique features. One key aspect of MI, the separation of the imputation phase from the analysis phase, can be advantageous in settings where the models underlying the two phases do not agree.