What statistical power means
Statistical power is the probability that a study will correctly detect an effect that truly exists — in other words, the chance of avoiding a false negative (Type II error). Power depends on the size of the effect you’re looking for, your sample size, and your chosen significance level.
How this calculator works
Enter the effect size you expect (Cohen’s d, a standardized measure of the difference between two group means), the sample size planned for each group, your significance level, and whether your test is one-tailed or two-tailed. The calculator uses the standard normal approximation for a two-independent-sample comparison to estimate the achieved power and the corresponding Type II error rate.
Larger effect sizes, larger sample sizes, and higher significance levels (alpha) all increase power. Many researchers aim for at least 80% power when planning a study. This tool is for general educational and planning purposes and uses an approximation rather than an exact test-specific calculation.