About the F-Test Calculator

The F-test compares two variances under the null hypothesis that they are equal. The statistic F = s₁² ÷ s₂² follows the F distribution with (n₁−1, n₂−1) degrees of freedom; the p-value here is computed directly from the regularized incomplete beta function, matching statistical software to several decimal places.

When to Use It

The two-sample F-test underpins ANOVA (comparing group means assumes comparable variances) and regression F-tests. Because it assumes normality, pair it with the Levene test for skewed data, and remember the test is two-tailed here — a very small F (s₁² ≪ s₂²) is just as informative as a large one.