LIKELIHOOD INFERENCE IN A CORRELATED PROBIT REGRESSION-MODEL
成果类型：
Article
署名作者：
OCHI, Y; PRENTICE, RL
署名单位：
Fred Hutchinson Cancer Center
刊物名称：
BIOMETRIKA
ISSN/ISSBN：
0006-3444
发表日期：
1984
页码：
531543
关键词：
摘要：
Equicorrelated binary observations are modeled using a multivariate probit regression model. Log likelihood derivatives are reduced to simple linear combinations of equicorrelated multivariate normal probabilities, which are approximated using the method of Mendell and Elston (1974). A data set with overdispersion illustrates the use of this model. This model was used to investigate chromosomal aberrations in humans exposed to radiation.