Learn Updated 2026-03-07 UTC

Effect Size Calculator (Cohen’s d, Hedges’ g, η², Odds Ratio) — GetCalcMaster

Effect size guide + calculator formulas: Cohen’s d, Hedges’ g, η²/partial η², correlation r, and odds ratio. Includes interpretation tips and common mistakes.

Effect size answers “how big is the effect?” (not just “is it significant?”). This page collects the most common effect size definitions and shows how to compute and interpret them.

Open Statistics Calculator Use Notebook Guides

Important: This page is educational. Effect size benchmarks vary by field; use domain-specific guidance when available.

What this calculator is

The Statistics Calculator is an interactive tool inside GetCalcMaster. It’s designed to help you explore scenarios, understand formulas, and document assumptions.

Key features

Covers multiple effect size families (mean differences, ANOVA, 2×2 tables)
Highlights when sign matters (direction) vs when magnitude matters
Includes quick “sanity checks” so you don’t report impossible values
Links to power/sample size planning and multiple‑comparisons corrections

Formula

Cohen's d = (M1 - M2) / s_pooled
s_pooled = sqrt(((n1-1)s1^2 + (n2-1)s2^2) / (n1+n2-2))

Hedges' g = J(df) * d,   df = n1+n2-2
J(df) ≈ 1 - 3/(4df - 1)

η² = SS_between / SS_total
partial η² = SS_effect / (SS_effect + SS_error)

Odds ratio (2×2) OR = (a*d)/(b*c)

Quick examples

Two training programs differ by 5 points; d standardizes that difference in SD units.
An ANOVA reports SS_between and SS_total; η² gives the proportion of variance explained.
A clinical study reports a 2×2 table; OR summarizes the association strength.

Verification tips

Check units: Cohen’s d and Hedges’ g are unitless (SD units).
For odds ratios, OR must be > 0 (negative OR indicates a calculation error).
η² and partial η² should be between 0 and 1.

Common mistakes

Reporting p-values without any effect size or uncertainty.
Mixing up η² and partial η² (they answer different questions).
Using Cohen’s d cutoffs mechanically without domain context.

How to use it (quick steps)

Pick the effect size that matches your outcome type (mean, proportion, contingency table, ANOVA).
Compute the effect size using the formula below (or in the stats calculator).
Interpret magnitude in context (domain benchmarks beat generic cutoffs).
Report the estimate with uncertainty (CI) when possible.
Use the effect size as input to power/sample size planning.