Effect Size

A standardized measure of the magnitude of an intervention’s effect, independent of sample size. The most common metric is Cohen’s d, calculated as the difference between two group means divided by their pooled standard deviation. Jacob Cohen’s benchmarks classify d = 0.2 as “small,” d = 0.5 as “medium,” and d = 0.8 as “large.”

Effect size is conceptually distinct from statistical significance (p-value): with large samples, trivially small differences can be statistically significant. Effect size answers the more useful question of “how practically meaningful is this difference?” In Meta-Analysis, effect sizes serve as the common currency for aggregating results across heterogeneous studies.