(a) For the pulp experiment show that neither the Bonferroni nor the Tukey
method declares any pair of treatments as different at the 0.01 level.
(b) How do you reconcile the finding in (a) with the result in Section 2.1 that
the F test rejects the null hypothesis H0 at the 0.05 level? After rejecting the
null hypothesis, do you expect the multiple comparison method to identify
at least one pair of treatments as different? (Hint: One is at the 0.01 level
while the other is at the 0.05 level.)
(c) Recall that the p value for the observed F statistic value 4.20 is 0.02. How
can you use this fact to reach the same conclusion in (a) without actually
performing the multiple comparisons? (Hint: Use the relationship between
the p value and the significance level of the F test.)