Effect Size Calculator

Compute Cohen's d for one-sample or two-sample mean differences.

Comparison type

Enter the means, standard deviations, and sample sizes for the selected comparison type.

How this effect size calculator works

This calculator reports Cohen's d, the standardized mean difference. Comparison type defaults to Two independent samples. You can switch to One sample vs baseline. The headline is d to three decimals. Details always show Mean difference and Interpretation. Two independent samples also show Pooled SD.

Empty on a required field is no result. Each standard deviation must be greater than 0. Two-sample sizes must be integers of at least 2 (decimals are floored). One sample vs baseline does not ask for a sample size — only Sample mean, Baseline / null mean, and Sample SD. Interpretation uses |d|: below 0.2 Negligible effect, at least 0.2 Small effect, at least 0.5 Medium effect, at least 0.8 Large effect. A positive d means group 1 (or the sample mean) is larger.

How to use the effect size calculator

  1. Choose Two independent samples (default) or One sample vs baseline.
  2. For two samples enter Group 1 mean, Group 1 SD, Group 1 size, Group 2 mean, Group 2 SD, and Group 2 size. For one sample enter Sample mean, Baseline / null mean, and Sample SD.
  3. Read d in the headline, plus Mean difference, Pooled SD when it applies, and Interpretation.
  4. Advanced options can be opened, but it only shows Reserved for future design details. Closing it does not change d.

Advanced options, and closing them

This section is empty of extra inputs. It only shows Reserved for future design details. Mean difference, Pooled SD, and Interpretation do not wait on Advanced options. Closing the section does not change the live result.

Cohen's d formulas

Two independent samples use a pooled standard deviation weighted by n − 1 in each group, then d = (mean₁ − mean₂) / s_p. One sample vs baseline is d = (sample mean − baseline) / sample SD. There is no n in the one-sample formula.

Pooled standard deviation
sp=(n1−1)s12+(n2−1)s22n1+n2−2
Two-sample Cohen's d
d=x¯1−x¯2sp

Worked examples

Example: 105 and 100, SDs 10 and 12, n = 50 each

Keep Two independent samples. Mean difference is 5. Pooled SD = √122 ≈ 11.045. d ≈ 0.453, so Interpretation is Small effect (0.2 ≤ |d| < 0.5).

Example: One sample vs baseline, 105 versus 100, SD = 10

Switch to One sample vs baseline. d = 5 ÷ 10 = 0.5, so Interpretation is Medium effect. There is no sample-size field in this mode. Closing Advanced options does not change d.

Example: n = 1 or SD = 0

A group size of 1 (or any value that floors below 2) is no result. Typed 0 for a standard deviation is no result. Empty required fields are no result.

Things to keep in mind

d is signed. Interpretation uses the absolute size. Completed results can be saved in this browser’s local history.

Effect size calculator FAQ

Which fields are required?

For Two independent samples: both means, both SDs greater than 0, and both sizes as integers ≥ 2. For One sample vs baseline: Sample mean, Baseline / null mean, and Sample SD greater than 0 — no n. Empty required fields are no result. Advanced options is optional and currently unused.

What happens when I close Advanced options?

Nothing in the result changes. The section only shows Reserved for future design details. Mean difference, Pooled SD, and Interpretation stay visible.

How is Interpretation decided?

From |d|: below 0.2 Negligible effect, at least 0.2 Small effect, at least 0.5 Medium effect, at least 0.8 Large effect. The sign of d does not change the label.

Does one-sample mode need a sample size?

No. One sample vs baseline only uses Sample mean, Baseline / null mean, and Sample SD. Two independent samples do need both group sizes.

Are group sizes floored?

Yes. Each size is floored to an integer of at least 2. n = 1 is no result. Typed 0 for an SD is no result.

Does this effect size calculator store my numbers?

Completed results can be saved in this browser’s local history so you can reopen them later. They stay on your device and are not sent to our servers or to analytics.