Lecture 15: Two-sample testing under heteroscedasticity
October 31st, 2024 (8th week of classes)Two-sample mean testing accounting for differences in sample variances
When the populations from which the samples are drawn cannot be assumed to have equal variances, the standard t-test is not appropriate for comparing their means. To determine whether the population variances differ significantly, we use the F-ratio test. If no significant difference is found, we assume homoscedasticity, meaning the populations have equal variances. However, if we cannot assume that the population variances are equal (i.e., they differ significantly), Welch’s modified t-test is applied, providing a more reliable comparison of the population means under heteroscedasticity.
Lecture
Slides: