Cohen's d is a standardized measure of the difference between two group means, expressed in standard deviation units. A d of 1.0 means the groups differ by one full standard deviation.

What counts as a small, medium, or large effect?

By Jacob Cohen's convention: |d| < 0.2 is negligible, 0.2–0.5 is small, 0.5–0.8 is medium, and ≥ 0.8 is large. These thresholds are guidelines, not hard rules — context matters.

What is Hedges' g and when should I use it?

Hedges' g corrects Cohen's d for positive bias when sample sizes are small (< 50). For large samples the two values are nearly identical. Prefer Hedges' g when n1 or n2 is under 20.

Which pooled SD formula does this calculator use?

It uses the weighted pooled SD: sqrt(((n1−1)·SD1² + (n2−1)·SD2²) / (n1+n2−2)), which is the standard formula for independent-samples Cohen's d.

Does the sign of d matter?

The sign indicates direction: positive means Group 1 scored higher, negative means Group 2 scored higher. Most conventions report the absolute value for magnitude, but direction is meaningful in context.

Can I use this for paired samples?

This calculator assumes independent groups. For paired (repeated-measures) designs, use the paired-t-test tool and compute d from the difference scores' mean and SD instead.

Cohen's d Effect Size Calculator

Name: Cohen's d Effect Size Calculator
Availability: InStock
Author: Nham Vu

Enter means, SDs, and sample sizes for two groups to get Cohen's d and Hedges' g with interpretation.

Group Parameters

1 Group 1

Mean (M₁)

Standard Deviation (SD₁)

Sample Size (n₁)

2 Group 2

Mean (M₂)

Standard Deviation (SD₂)

Sample Size (n₂)

Summary

Enter means, SDs, and sample sizes for two groups to get Cohen's d and Hedges' g with interpretation.

How it works

Enter the mean, standard deviation, and sample size for Group 1.
Enter the same values for Group 2.
Click Calculate to compute the pooled standard deviation.
Cohen's d = (M1 − M2) / pooled SD is displayed with sign and magnitude.
Hedges' g applies a small-sample correction factor (J) for n < 50.
The effect size is interpreted as small (< 0.2), medium (≈ 0.5), or large (≥ 0.8).

Use cases

Report effect size alongside a t-test in an academic paper.
Compare pre- and post-intervention scores in clinical research.
Assess practical significance beyond a p-value in A/B tests.
Power analysis: determine required sample size for a target d.
Meta-analysis: standardize effect sizes across studies.
Psychology and education research reporting.
Quality-improvement projects comparing two process conditions.

Frequently Asked Questions

Last updated: 2026-06-11 · Reviewed by Nham Vu