each test

F-test

compares two population variances and tests whether two normal populations, sampled independently, have the same variance

Independent t-test

tests a claim about the difference between two population means using two independent samples from normal populations with equal variances

Welch t-test

Test whether the mean of two normal populations are equal typically when the population variances of two normal populations are unequal

Paired t-test

compares the mean of the differences between each pair’s observations (e.g. “before” and “after”). There is one sample of pairs with two observations.

Wilcoxon rank-sum test

the non-parametric alternative to the independent t-test. It uses two independent samples, compares medians rather than means, and assumes both populations have the same shape

Wilcoxon signed-rank test

the non-parametric alternative to the paired t-test. Uses one sample of paired observations, compares the median of the differences, and assumes the differences are symmetric