EMPIRICAL BAYES METHODS FOR 2-WAY CONTINGENCY-TABLES
成果类型：
Article
署名作者：
LAIRD, NM
署名单位：
Harvard University
刊物名称：
BIOMETRIKA
ISSN/ISSBN：
0006-3444
发表日期：
1978
页码：
581590
关键词：
摘要：
An empirical Bayes method for smoothing 2-way tables is presented. It is based on the use of the log linear model and a normal prior distribution. Estimation of the variance component in the prior is discussed, and 2 approximations are considered, 1 which utilizes the EM [expectation maximization] algorithm.