o A post-hoc test is needed after we complete an ANOVA in order to determine which groups differ from each other. o Do not conduct a post-hoc test unless you found an effect (rejected the null) in the ANOVA problem. If you fail to reject the null, then there are no differences to find. Post HOC Testing
Effect of drug doses on AST activity SourceSSdfMSF cal. Between groups Within groups (residual) Total ANOVA Table F cal (5.76) > F tab (2.64)
Tukey’s HSD (Honestly significance difference) Post-hoc test The critical value for comparison between two averages Sample size /group Number of groups = number of means = r Total sample size (for all groups) Number of groups = number of means = r Number of groups Critical q value (tabulated)tabulated (0.05, 0.01) N – g = df of the WITHIN MS
Effect of drug doses on AST activity n88888 Sum Mean Variance (s) g = 5 Df within = N - g = 35 SourceSSdfMSF cal. Between groups Within groups (residual) Total MS within = 12
q(5, 35, 0.05) = 4.07Within MS = 12n /group= 8 x3 - x1 = 8.26 > 4.96; x3 - x5 = 4.63 < 4.96; x2 - x1 = 4.63 < 4.96 Significant Not significant and so on.