Statistical Methods for Meta-Analysis

by Larry V. Hedges and Ingram Olkin

Book Overview

The main purpose of this book is to address the statistical issues for integrating independent studies. There exist a number of papers and books that discuss the mechanics of collecting, coding, and preparing data for a meta-analysis, and we do not deal with these.
Because this book concerns methodology, the content necessarily is statistical, and at times mathematical. In order to make the material accessible to a wider audience, we have not...

• Format: Hardcover
• Language: English
• ISBN: 0123363802
• ISBN13: 9780123363800
• Release Date: August 1985
• Publisher: Academic Press
• Length: 369 Pages
• Weight: 1.60 lbs.
• Dimensions: 1.2" x 6.3" x 9.3"

Customer Reviews

masterpiece on meta-analyses

Prior to the publication of this text in 1984, there was a scattered statistical literature on combining information from several data sources or experiments to produce stronger statistical analyses. The idea dates back to an early paper by R. A. Fisher for combining p-values. Hedges and Olkin with this book provided a systematic and rigorous treatment of the subject. They had seen the technique being used (and sometimes abused) in the social sciences and in education in particular. This book was the first source to compile the results from a scattered literature into a systematic treatment of the classical statistical approach to meta-analysis. It is still the best source for the subject. Today meta-analysis is common in studies in medical research. Similar Bayesian approaches through the use of Bayesian Hierarchical Models are also aimed at the same goals as meta-analysis. See for example the recent text by Stangl and Berry.