How to Use Statistical Power Calculator

About this tool

Power or required sample size for t-tests, proportions and correlations.

How to use Statistical Power Calculator

1. Choose the design and whether to solve for power or sample size.
2. Enter the effect size (d, proportions or r) and alpha.
3. Read the power, or the sample size needed to reach your target power.

Worked example

Detecting d = 0.5 with 50 people per group at α = 0.05 (two-sided) gives about 70% power; 64 per group are needed for 80%.

What power should I aim for?

80% is the usual minimum and 90% is common in confirmatory trials. Lower power means a real effect is easily missed.

Where does the effect size come from?

From pilot data, earlier studies or the smallest effect that would matter in practice. Avoid inflated estimates from small studies.

Put this guide into practice

• Statistical Power Calculator — Power or required sample size for t-tests, proportions and correlations.