ALTERNATIVE CONDITIONS FOR IGNORING THE PROCESS THAT CAUSES MISSING DATA
成果类型：
Article
署名作者：
GOFFINET, B
刊物名称：
BIOMETRIKA
ISSN/ISSBN：
0006-3444
DOI：
10.2307/2336161
发表日期：
1987
页码：
437439
关键词：
摘要：
It is demonstrated that, when a complete sufficient statistic exists, weaker conditions than those of Rubin (1976) are sufficient to allow one to make inferences about the sampling distribution in the case of missing data, where the process that causes missing data is not independent of the data. An example from animal breeding is presented.
来源URL：