The Essential Guide to Effect Sizes: Statistical Power, Meta-Analysis, and the Interpretation of Research Results

by Paul D. Ellis

Overview

This succinct and jargon-free introduction to effect sizes gives students and researchers the tools they need to interpret the practical significance of their results. Using a class-tested approach that includes numerous examples and step-by-step exercises, it introduces and explains three of the most important issues relating to the practical significance of research results: the reporting and interpretation of effect sizes (Part I), the analysis of statistical power (Part II), and the meta-analytic pooling of effect size estimates drawn from different studies (Part III). The book concludes with a handy list of recommendations for those actively engaged in or currently preparing research projects.

Product Details

ISBN-13:	9780521142465
Publisher:	Cambridge University Press
Publication date:	07/01/2010
Pages:	188
Product dimensions:	6.80(w) x 9.60(h) x 0.40(d)

About the Author

Paul D. Ellis is Professor in the Department of Management and Marketing at Hong Kong Polytechnic University, where he has taught research methods for nearly fifteen years. His research interests include trade and investment issues, marketing and economic development, international entrepreneurship, and economic geography. Professor Ellis has been ranked as one of the world's most prolific scholars in the field of international business.

Table of Contents

List of figures ix

List of tables x

List of boxes xi

Introduction xiii

Part I Effect sizes and the interpretation of results 1

1 Introduction to effect sizes 3

The dreaded question 3

Two families of effects 6

Reporting effect size indexes-three lessons 16

Summary 24

2 Interpreting effects 31

An age-old debate - rugby versus soccer 31

The Problem of interpretation 32

The importance of context 35

The contribution of knowledge 38

Cohen's controversial criteria 40

Summary 42

Part II The analysis of statistical power 45

3 Power analysis and the detection of effects 47

The foolish astronomer 47

The analysis of statistical power 56

Using power analysis to select sample size 61

Summary 66

4 The painful lessons of power research 73

The low power of published research 73

How to boost statistical power 81

Summary 82

Part III Meta-analysis 87

5 Drawing conclusions using meta-analysis 89

The problem of discordant results 89

Reviewing past research - two approaches 90

Meta-analysis in six (relatively) easy steps 97

Meta-analysis as a guide for further research 109

Summary 112

6 Minimizing bias in meta-analysis 116

Four ways to ruin a perfectly good meta-analysis 116

1 Exclude relevant research 117

2 Include bad results 122

3 Use inappropriate statistical models 127

4 Run analyses with insufficient statistical power 130

Summary 131

Last word: thirty recommendations for researchers 134

Appendices

1 Minimum sample sizes 138

2 Alternative methods for meta-analysis 141

Bibliography 153

Index 170

Editorial Reviews

Assessing the substantive significance of research is essential for both scientific progress and practical implications. This authoritative and well-written book gives relevant examples of key issues and offers practical guidelines for assessing the importance of research findings. The book concludes with clear recommendations for designing and carrying out good research and for assessing and reporting research findings.”
William H. Starbuck, Professor-in-Residence, University of Oregon, and Professor Emeritus, New York University

“Paul Ellis writes with a light touch, explains well, and uses numerous practical examples. He focuses on four of the issues that are central to the statistical changes now sweeping many disciplines – effect sizes, confidence intervals, power, and meta-analysis. This is a highly readable, highly practical book. It will be invaluable to anyone who wishes to contribute to – or even just understand – the research of the future.”
Geoff Cumming, Emeritus Professor, School of Psychological Science, La Trobe University, Australia

From the Publisher