Statistical Methods in Meta-Analysis

Publisher Website
Google Scholar
Abstract
This chapter addresses only systematic review and meta-analysis. It first introduces the concept heterogeneity then describes how heterogeneity affects the ability to draw valid conclusions from the summary estimate of effect size in study data that are analyzed in a meta-analysis. The difference between the assumptions that underlie the use of a fixed-effects and a random-effects model are explained. The chapter describes the Mantel Haenszel and the Peto methods for calculating a summary measure of effect size in a meta-analysis. These are the two methods used most commonly for information from randomized trials when the analysis is based on the fixed-effects model. General variance-based methods for estimating a summary measure of effect are presented. These methods are often applicable in the meta-analysis of observational data. The formulae used to do statistical tests of heterogeneity are given. Finally, the chapter describes the DerSimonian Laird method for calculating summary estimates of effect based on a random effects model.

This publication has 0 references indexed in Scilit: