Beyond Significance Testing: Reforming Data Analysis Methods in Behavioral Research

"This book is a follow-up to the report of Leland Wilkinson and the Task Force on Statistical Inference (TFSI; 1999) of the American Psychological Association (APA) and the fifth edition of the Publication Manual of the American Psychological Association (APA, 2001). The goals of this book are to (a) review the now-large literature across many different disciplines about shortcomings of statistical tests; (b) explain why these criticisms have sufficient merit to justify change in data-analysis practices; (c) help readers acquire new skills concerning effect size estimation and interval estimation for effect sizes; and (d) review additional alternatives to statistical tests, including bootstrapping and Bayesian statistics. An additional goal is related to the criticism that the most recent Publication Manual calls for change in data analysis practices but does not give examples. Numerous examples with actual research results are presented throughout this volume. This book is written for researchers and students in psychology and related areas who may not have strong quantitative backgrounds. It assumes that the reader has had at least one undergraduate-level course in behavioral science statistics. Each substantive chapter begins with a review of fundamental statistical issues but does not get into the minutia of statistical theory. Exercises with answers for the chapters are also available on the Web site"--Preface. (PsycINFO Database Record (c) 2005 APA, all rights reserved)