Power Analysis Calculator
Run a statistical power analysis online: calculate the sample size required to reach a target power, or the power your test achieves with a given sample size. The calculator runs free in the browser, with no installation, as an online alternative to desktop tools like G*Power.
What is statistical power?
Statistical power is the probability that a hypothesis test detects an effect that truly exists. It equals 1 - β, where β is the probability of a type II error (missing a real effect). A power of 80% (0.8) is the most common planning target; studies with high stakes often aim for 90%.
A priori vs. post-hoc power analysis
An a priori power analysis is run before data collection: you specify the expected effect size, the significance level alpha, and the target power, and the calculator returns the required sample size. This is the recommended way to plan a study. A post-hoc power calculation works in the other direction: you enter the sample size you already have and get the power the test achieves for a given effect size. Switch between the two with the "Calculate sample size" and "Calculate power" options.
What you need to enter
- Significance level alpha (commonly 0.05) and whether the test is one- or two-sided
- The effect size you want to detect (e.g. a mean difference or Cohen's d)
- Target power, or the available sample size if you solve for power
Supported tests
- Two-sample t-test
- One-sample t-test
- Paired t-test
- One-sample proportion test
- Two-sample proportion test
- One-sample Poisson rate test
- Two-sample Poisson rate test
If you want to plan the precision of an estimate instead of testing a hypothesis, use the estimation mode of the sample size calculator.