📏 Effect Size Calculator (Cohen's d)
Enter two groups' means, SDs and sizes to get Cohen's d — the standardized effect size — plus whether it's small, medium or large.
Group 1
Group 2
Cohen's d
0.667
Pooled SD
15
medium effect size
By Cohen's conventional benchmarks (|d| ≈ 0.2 small, 0.5 medium, 0.8 large), a d of 0.67 is a medium effect — the group means differ by about 0.67 pooled standard deviations.
Cohen's d expresses the difference between two group means in units of their pooled standard deviation, giving the magnitude of an effect independent of sample size — a useful complement to a p-value, which only tells you whether an effect is detectable. The small/medium/large labels are rules of thumb, not hard cut-offs; interpret them in your field's context. 🔒 Computed in your browser.
How the effect size calculator (cohen's d) works
Cohen's d divides the difference between the two group means by their pooled standard deviation, expressing the gap in standard-deviation units. The tool computes the pooled SD from both groups' SDs and sizes, then d, and labels its magnitude using Cohen's conventional benchmarks (about 0.2 small, 0.5 medium, 0.8 large).
Effect size answers the question a p-value can't: not “is there a detectable difference?” but “how big is it?”. Because significance depends on sample size, a trivial difference can be highly significant in a huge study, while a large, important effect can miss significance in a small one — so reporting Cohen's d alongside a test is best practice. The small/medium/large labels are rough guides, not universal truths; a “small” d can matter a great deal in some fields. It all runs locally in your browser.
Frequently asked questions
What is Cohen's d?
A standardized effect size: the difference between two group means divided by their pooled standard deviation. A d of 1.0 means the means differ by one standard deviation. It's independent of sample size, unlike a p-value.
What counts as a small, medium or large effect?
Cohen's rules of thumb are roughly 0.2 (small), 0.5 (medium) and 0.8 (large), with values under ~0.2 negligible. These are conventions — interpret the size in the context of your field and what's practically meaningful.
Why report effect size as well as a p-value?
Because significance depends on sample size: a tiny, unimportant difference can be significant in a large sample, and a large, important one can be non-significant in a small sample. Effect size measures the magnitude regardless of n.
How is the pooled standard deviation calculated?
It combines both groups’ variances weighted by their degrees of freedom: √[((n₁−1)·SD₁² + (n₂−1)·SD₂²) / (n₁+n₂−2)]. This is the standard denominator for Cohen’s d with two independent groups.
Is my data uploaded?
No — the calculation runs entirely in your browser and works offline.