TimelyScholarFree Tools › Power Analysis & Sample Size Calculator
Work out how many participants you need, or the power you will have, for t-tests and comparisons of two proportions. Uses the exact non-central t method used by G*Power.
FreeNo account neededYour data stays in your browser
| Sample size per group | 64 |
|---|---|
| Total sample size | 128 |
| Achieved power | 0.801 |
Exact power from the non-central t distribution (two-sided), the method used by G*Power. Increase the sample size to allow for expected dropout.
Two-sample t-test, paired/one-sample t-test or two proportions.
Sample size or power.
Effect size, significance level and target power or sample size.
A power analysis tells you the sample size needed to detect an effect of a given size with a given probability (power), usually 80% or 90%, at a chosen significance level, usually 5%.
The expected effect size should come from previous studies, a pilot or the smallest effect that would matter in practice. Cohen's conventional values for d are 0.2 (small), 0.5 (medium) and 0.8 (large).
80% is the conventional minimum and 90% is common for trials; higher power needs a larger sample.
The calculated n is the number you need to analyse, so recruit extra to allow for expected dropout or missing data.