Cohen’s d Effect Size Calculator
Compute Cohen’s d — the standardized difference between two group means — from raw data or from summary statistics. You also get Hedges’ g (a small-sample correction), a 95% confidence interval, and a plain-language interpretation.
How to use it
Why report an effect size
A p-value tells you whether a difference is likely real; Cohen’s d tells you how big it is, in standard-deviation units, so it’s comparable across studies and scales: \[d = \frac{\bar{x}_1 - \bar{x}_2}{s_{pooled}}\]
- d ≈ 0.2 small · 0.5 medium · 0.8 large (rough conventions — interpret in context).
- Hedges’ g applies a small-sample correction; prefer it when groups are small.
- Report the confidence interval too — a wide interval means the effect size itself is uncertain.
With a large enough sample, a trivial difference can be “statistically significant” yet have a tiny d — which is exactly why you report both.
Do it in R
# base R
pooled <- sqrt(((length(a)-1)*var(a) + (length(b)-1)*var(b)) / (length(a)+length(b)-2))
(mean(a) - mean(b)) / pooled
# or effsize::cohen.d(a, b)Full walkthrough: Cohen’s d and effect size in R.
FAQ
Frequently asked questions
Cohen’s d or Hedges’ g?
They answer the same question, but Hedges’ g corrects a slight upward bias in d for small samples. With large groups they’re nearly identical; with small groups, prefer g.
Can I get d from a t-test?
Yes — for two independent groups, d ≈ t × √(1/n₁ + 1/n₂). This calculator uses the group means and SDs directly, which is cleaner.
Effect sizes feed directly into sample-size planning. Need the whole analysis? We can help.