EXST 2201 : 2201c Post Hoc Tests
Document Summary
If we conduct an anova method and find an insignificant p-value ( that all population means can be considered to be equal, and we have all the information we can get out of the sample with the anova method. But, what happens if we get a significant. If the p-value is significant this means that at least one of the population means is different from the others, and all means could be different from each other. We can get answers to these questions with two post-hoc tests (post-hoc means after the fact"): multiple comparisons of population means; and contrasts. Suppose you perform a one-way anova and reject the null hypothesis, so not all of the population means are equal. The very next question is, which means are not equal?". Then comes the question, which mean is the largest (or smallest)?". In general, what is the relationship among all the means.
