Interpreting effect sizes: Toward a quantitative cumulative social psychology

Abstract

Improved research practice is based on estimation of effect sizes rather than statistical significance. We discuss the challenging task of interpreting effect sizes in the research context, with particular attention to social psychological research. We emphasize the need to acknowledge the uncertainty in an effect size estimate, as signaled by the confidence interval. Interpretation must consider the independent variables, participants, measures, and other aspects of the research. Comparison with other results in the research field, and consideration of theoretical and practical implications are useful strategies. Researchers should consider the possible value of agreeing on benchmarks to help guide effect size interpretation, at least within focused research fields. More broadly, researchers should wherever possible think of experimental manipulations as well as results in quantitative terms. Doing so is fundamental for designing ingenious, informative experiments, understanding research results and their implications, developing theory, and building a quantitative cumulative social psychology