UsefulVerse
Language · English

Free to use, no account

Statistical Power Calculator

Plan a two-group comparison of means. Estimate power from a sample size, or estimate the participants needed for a target power.

Cohen’s d is the expected difference between group means divided by the shared standard deviation. Use a defensible estimate from prior evidence or a meaningful minimum effect—not a result chosen after seeing the data.

Approximation for two independent, equally sized groups comparing means with a normal (z) model. It is not the exact small-sample t-test calculation.

Model reference Statsmodels: two-sample normal power model

What does statistical power mean?

Power is the chance that a planned test detects the specified effect when that effect is real. It depends on the effect size, sample size and significance level.

Frequently asked questions

What does statistical power mean?

Power is the chance that a planned test detects the specified effect when that effect is real. It depends on the effect size, sample size and significance level.

Are my study assumptions uploaded?

No. The calculation runs in this browser. Your assumptions are not uploaded or saved by this tool.

What does 80% power mean?

Under the assumptions entered, an 80% estimate means the planned test would detect the specified effect about 80% of the time if that effect were real. It is not an 80% chance that a result is true.

What is Cohen’s d?

Cohen’s d is a standardized difference between two means: the expected gap divided by the common standard deviation. The result depends strongly on the effect you choose.

Does this replace a full power analysis?

No. This browser estimate covers a balanced two-group means comparison with a normal approximation. It does not model unequal group sizes, paired data, proportions, ANOVA, clustered or repeated measures, covariates, exact t tests, multiple testing or study-specific design constraints.