How to Report Effect Size in APA Style
APA 7 expects more than a p-value. For every inferential test you should report an effect size — and, where possible, its confidence interval — because the effect size, not the p-value, tells the reader how big the difference actually is.
The right effect size depends on the test: Cohen's d for mean differences, η² (or partial η²) for ANOVA, and r for correlation. This guide shows the formula, the APA sentence, and the interpretation thresholds for each.
Effect size by test
| Test | Effect size | Small / Medium / Large |
|---|---|---|
| t-test | Cohen's d | 0.2 / 0.5 / 0.8 |
| ANOVA | η² (partial η²) | 0.01 / 0.06 / 0.14 |
| Correlation | r | 0.1 / 0.3 / 0.5 |
Cohen's d for t-tests
Report the standardized mean difference with its CI, e.g. d = 0.62, 95% CI [0.18, 1.05], and pair it with the descriptive means.
Eta-squared for ANOVA
Give partial η² for each effect; remember thresholds are guidelines, not laws — interpret in the context of your field.
APA sentence templates
Use a consistent pattern: statistic, df, p, then the effect size and CI in brackets, so reviewers can scan results quickly.
Run this analysis on your own data — free, in your browser.
Open MindStat →