SMALL SAMPLES IN CONTINGENCY-TABLES
成果类型：
Article
署名作者：
COX, MAA; PLACKETT, RL
刊物名称：
BIOMETRIKA
ISSN/ISSBN：
0006-3444
发表日期：
1980
页码：
113
关键词：
摘要：
The analysis of some contingency tables is based on hierarchical log linear models. Inferences about sets of parameters can be made from conditional distributions. Three ways of improving the asymptotic methods generally used in practice are discussed. They comprise better approximations to moments of cell frequencies than those derived from the iterative scaling procedure, exact distributions obtained by enumerating all tables consistent with given marginal totals and simulated random sampling for tables where exact enumeration is impossible.