Emphasis on effect sizes is rapidly rising since more than 20 journals in various fields of research now require that authors of research reports provide estimates of effect size. Especially in applied research, results need to be supplemented with estimates of how different the average results for studied groups are or how strong the association between variables is. Those who apply the results of research often need to know more than that one therapy, teaching method, marketing campaign, or medication that appears to be better than another; they often need evidence of how much better it is (estimated effect size). The purpose of this book is to inform a broad readership - broad with respect to fields of research and extent of knowledge of general statistics - about a variety of measures and estimators of effect sizes for research, their proper applications and interpretations, and their limitations. It focuses on both analyzing post-research results in terms of size of the obtained effects and also the analysis of data from an individual piece of research (called primary research).
The text also deals with a broad variety of kinds of effect sizes for diverse variables, designs, circumstances, and purpose; cites alternative viewpoints; pays much attention to the statistical assumptions of methods; and includes more than 300 references. The approach encompasses detailed discussions of standardized differences between measures, some of the correlational measures, strength of association, confidence intervals, other common methods, and less-known measures, such as stochastic superiority. Effect Sizes for Research: A Broad Practical Approach is intended as a supplement for graduate courses in statistics in the fields of psychology, education, the social sciences, business, management, and medicine. It is also a valuable source for professional researchers, graduate students who are analyzing data for a master's or doctoral thesis, or advanced undergraduates.