Effect Size Calculator
Calculate Cohen's d, Hedges' g, and Glass's delta to measure the practical significance of differences between two groups.
About this calculator
This calculator computes Cohen's d, Hedges' g, and Glass's delta — three related measures of the standardized difference between two group means — from each group's mean, standard deviation, and sample size. Cohen's d divides the mean difference by a Pooled Standard Deviation built from both groups' variability and sample sizes (lines 14-19); Hedges' g then applies a small-sample bias correction, 1 − 3/(4×df − 1) (line 23), that shrinks toward 1 as sample sizes grow. Glass's delta instead divides the mean difference by Group 2's Standard Deviation alone (line 27) and, unlike the other two, is completely unaffected by Group 1's Standard Deviation or either group's sample size.
Group 1 Mean shows a larger measured effect on Cohen's d than Group 2 Mean under a sensitivity check, but this reflects their different default magnitudes (78 vs 72), not an asymmetry in the formula — the true partial derivative with respect to either mean has identical magnitude, 1 / Pooled Standard Deviation (line 11). Neither group's mean has any effect on Pooled Standard Deviation, which is computed purely from the two standard deviations and sample sizes. This calculator does not account for unequal-variance corrections beyond Glass's delta's single-group choice — it offers no Welch-style adjustment, so if the two groups' true variances differ substantially, Cohen's d and Hedges' g's shared pooled-variance assumption may understate or overstate the true standardized difference.
Inputs
Results
Cohen's d
0.54
Hedges' g (bias-corrected)
0.54
How to Use This Calculator
- Enter Group 1 Mean, Group 2 Mean, and Group 1 Standard Deviation.
- Set Group 2 Standard Deviation, Group 1 Sample Size, and Group 2 Sample Size.
- Review Cohen and Hedges.
- Use Glass and Pooled Standard Deviation to inform your decision.
- Use the chart to visualize the results and explore different scenarios by adjusting inputs.
How the result changes with Group 1 Mean
| Group 1 Mean | Cohen's d | Hedges' g (bias-corrected) |
|---|---|---|
| 39 | -2.99 | -2.95 |
| 59 | -1.18 | -1.16 |
| 117 | 4.07 | 4.02 |
| 195 | 11.14 | 10.99 |
What each input means
- Group 1 Mean
- Mean of the first (treatment or experimental) group.
- Group 2 Mean
- Mean of the second (control or comparison) group.
- Group 1 Standard Deviation
- Standard deviation of the first group.
- Group 2 Standard Deviation
- Standard deviation of the second group.
- Group 1 Sample Size
- Number of observations in the first group.
- Group 2 Sample Size
- Number of observations in the second group.
How this is calculated
Worked example, using the default values
- Identify Input Parameters4 parametersGroup 1 Mean = 78, Group 2 Mean = 72, Group 1 Standard Deviation = 10, Group 2 Standard Deviation = 12 = 6 input(s) provided
- Calculate Cohen's dCohen's d0.5432 = 0.5432
- Calculate Hedges' gHedges' g0.5362 = 0.5362
- Calculate Glass's DeltaGlass's Delta0.5 = 0.5
- Calculate Pooled Standard DeviationPooled Standard Deviation11.0454 = 11.0454
Engine last updated . Checked against 2 independently-derived tests — how we verify calculators. Built by Paul Gunder, a software engineer, not a licensed financial, medical, or legal professional.
Frequently Asked Questions
Why does Group 1 Mean show a bigger effect on Cohen's d than Group 2 Mean, if both means enter the formula the same way?
It's not that Cohen's d weighs Group 1 more heavily — the partial effect of each group mean on the mean difference is identical in magnitude, 1 / Pooled Standard Deviation either way (line 11). Group 1 Mean's default of 78 is simply a larger number than Group 2 Mean's 72, so an equal proportional nudge produces a bigger absolute swing, which is what a sensitivity check picks up — not a difference in how the formula treats the two groups.
Do Group 1's Standard Deviation and sample size affect Glass's Delta?
No. Glass's Delta is defined here as the mean difference divided by Group 2's Standard Deviation alone (line 27) — Group 1 Standard Deviation, Group 1 Sample Size, and Group 2 Sample Size never appear in that formula, unlike Cohen's d and Hedges' g, which pool both groups' variability and sample sizes together.
Does either group's mean affect the Pooled Standard Deviation?
No — Pooled Standard Deviation is built entirely from both groups' standard deviations and sample sizes (lines 14-17); it measures how spread out each group's data is, which is mathematically independent of where the two groups' averages happen to sit.
What's the difference between Cohen's d and Hedges' g in this calculator?
Hedges' g multiplies Cohen's d by a small-sample bias-correction factor, 1 − 3/(4×df − 1), where df is the pooled degrees of freedom (line 23) — at large sample sizes like the calculator's default of 30 per group, that correction factor sits very close to 1, so the two outputs stay nearly identical; it matters more when sample sizes are small.
Related Calculators
The questions that sit next to this one — chosen by subject, including calculators filed under a different category.
Power Analysis Calculator
Calculate the required sample size for a study given the effect size, significance level, and desired statistical power.
StatisticsT-Test Calculator
Calculate the t-statistic, degrees of freedom, and approximate p-value for a one-sample t-test.
StatisticsZ-Score Calculator
Calculate the z-score (standard score) for any value in a normal distribution. Find the percentile ranking and probability associated with your data point.
More in Math & Statistics.