Premium
Understanding and testing for heterogeneity across 2×2 tables: application to meta‐analysis
Author(s) -
Berry Scott M.
Publication year - 1998
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/(sici)1097-0258(19981030)17:20<2353::aid-sim923>3.0.co;2-y
Subject(s) - study heterogeneity , bayes' theorem , spatial heterogeneity , homogeneous , meta analysis , econometrics , bayesian probability , computer science , bayes factor , genetic heterogeneity , statistics , mathematics , ecology , biology , confidence interval , medicine , biochemistry , combinatorics , gene , phenotype
A question of interest in a meta‐analysis is whether the studies considered are homogeneous. This paper addresses two forms of heterogeneity. Additive heterogeneity occurs when a particular treatment performs differently in different studies. Interactive heterogeneity occurs when the relative performance of two treatments varies with the study. This paper discusses the use and calculation of Bayes factors to test for both forms of heterogeneity. I consider three hierarchical models. One exhibits both forms of heterogeneity, a second exhibits only additive heterogeneity, and the third model has neither form of heterogeneity. I use a method based on bridge sampling for calculating the Bayes factors between the models. I consider two examples: in one both forms of heterogeneity seem to be present and in the other there seems to be additive heterogeneity but not interactive heterogeneity. © 1998 John Wiley & Sons, Ltd.