ANOVA: Post-Hoc Testing

The one-way ANOVA framework initially tests the global hypothesis that at least one group mean is different from the others, but it does not tell you which pairwise comparisons are different. For this we must use post-hoc testing. In this lecture we discuss various strategies that have been developed and used for one-way ANOVA and provide examples in R and SAS.


Table of Contents:

00:00 - Intro Song
00:20 - Welcome
00:51 - Motivation
03:03 - Strategy 1: No Formal Correction
04:01 - Least Significant Difference (LSD)
10:03 - Strategy 2: Formal Correction
12:55 - Bonferroni Correction and Dunn's Test
14:42 - Tukey's HSD Example
15:31 - Dunnett's Test Example
16:14 - Closing Comments