Cohen’s d benchmarks define small, medium, and large effects in psychology

Evidence

In our analysis, we used two indicators of effect size (Cohen’s d and Pearson’s r), with larger effect sizes signifying stronger relationships between intergroup contact and prejudice. Cohen’s d represents the difference between the means of the contact and noncontact groups given in standard score units (or z-scores). For typical effects found in psychological research, a d of 0.25 is a small effect, 0.50 a medium effect, and 0.75 a large effect (Cohen, 1988). Results reported here derive from a fixed-effects model. — John F. Dovidio, Peter Glick, Laurie A. Rudman, On the Nature of Prejudice, 1683

Categorization

• DEFINE: Useful benchmark calibration: d of .25/.50/.75 as small/medium/large, and the r values correspondingly.