Premium
Maximum likelihood estimation and likelihood ratio test for square tables with missing data
Author(s) -
Shih W. J.
Publication year - 1987
Publication title -
statistics in medicine
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.996
H-Index - 183
eISSN - 1097-0258
pISSN - 0277-6715
DOI - 10.1002/sim.4780060111
Subject(s) - categorical variable , missing data , statistics , maximum likelihood , likelihood ratio test , restricted maximum likelihood , chi square test , mathematics , score test , likelihood principle , estimation , maximum likelihood sequence estimation , expectation–maximization algorithm , computer science , quasi maximum likelihood , management , economics
Missing data complicate the analysis of paired categorical data. This paper considers with the use of the EM algorithm, the maximum likelihood estimation and likelihood ratio test for incomplete square tables with missing data. An example involving the susceptibility of micro‐organisms to antimicrobial drugs illustrates the procedure.