Cohen's h Calculator
Measure the effect size for the difference between two proportions. Enter both proportions as percentages.
Learn how to calculate it yourselfEnter your values
Results update as you type.
Cohen's h
small effect
Calculate it yourself
Compare proportions of 60% and 40% on Cohen’s arcsine-transformed scale.
Follow this worked example, then repeat the steps with your own numbers.
Convert percentages to proportions
p₁ = 0.60; p₂ = 0.40.Transform each proportion
φ₁ = 2 × arcsin(√0.60) ≈ 1.77215. φ₂ = 2 × arcsin(√0.40) ≈ 1.36944.Use radians, not degrees, for the inverse sine.
Subtract the transformed values
h = φ₁ − φ₂ ≈ 0.40272. Magnitude |h| ≈ 0.403.Changing the group order reverses the sign but leaves the magnitude unchanged.
Use your PaperSurvey.io results
Convert the two groups’ observed outcome counts to proportions and compare them with Cohen’s h here.
What Cohen's h is for
Cohen's h is the effect size for the difference between two proportions, such as conversion rates or the share choosing an answer in two groups. It uses an arcsine transformation so that a given gap counts as a larger effect near 0% or 100% than it does in the middle, where proportions have more room to move by chance.
Reading the size
By Cohen’s conventions, 0.2 is a small effect, 0.5 is medium and 0.8 is large. Unlike a raw difference in percentage points, h is comparable across studies and is what A/B test power and sample size calculations are usually based on.
Frequently asked questions
How is this different from just subtracting the percentages?
A 5-point gap means something different at the extremes than in the middle. Cohen’s h adjusts for that so effects are comparable regardless of where the proportions sit.
Get Started with PaperSurvey.io Software
Start your 14-day free trial now, no credit card required.