Cohen’s d Calculator
States how big a difference is, in standard deviations, regardless of sample size.
Cohen’s d
—
Share sends a link that reopens these numbers. Copy details pastes the full breakdown as a list.
Hedges’ g —
Pooled standard deviation —
Conventional label —
Reading this —
The formula
d = (x̄₁ − x̄₂) ÷ s_pooled s_pooled = √(((n₁ − 1)s₁² + (n₂ − 1)s₂²) ÷ (n₁ + n₂ − 2)) g ≈ d × (1 − 3 ÷ (4(n₁ + n₂ − 2) − 1))
Hedges’ g removes a small upward bias in d, which matters only for small samples.
What to watch out for
A p-value depends heavily on sample size. An effect size does not, so report both when you can.
Frequently Asked Questions
What is a worked example?
Means of 15 and 13, with standard deviations of 3 and 4, in groups of 30 and 25, give d = 0.573.
What does d = 0.5 mean?
The means are half a standard deviation apart. If both groups are normal, the average of the higher one is at about the 69th percentile of the other.