STAT 3006 Lecture Notes - Lecture 10: Multiple Comparisons Problem, Analysis Of Variance
Document Summary
To check the assumptions or normality of the response and equality of variance for the difference treatment combinations, examine the residuals. Anova, the residuals are the deviations of the observations from their respective treatment combination samples means. (cid:1870)(cid:1857)(cid:1871)(cid:1856)(cid:1873)(cid:1864)=(cid:1856)(cid:1872) (cid:1868)(cid:1867)(cid:1866)(cid:1872) (cid:1865)(cid:1857)(cid:1866) (cid:1856)(cid:1872) (cid:1868)(cid:1867)(cid:1866)(cid:1872) Left: the residuals from the capsule experiment look approximately normal with the exception of two outliers, but neither are extreme enough to warrant any concerns. Right (residual plot): there appears to be more variation for the dissolve times for type c capsules being dissolved in gastric fluid. These combinations produced the two mild outliers seen in the normal quantile plot (see high / low residual values around time t = 50). Generally, we worry when the variation increases with the treatment combination mean. When interactions exist, the main effects involved are important but cannot be discussed separetly. Multiple comparisons can still be conducted to compare different treatment level means.