Refer to Exercise 13 in Section 9.1.

a. Use the Bonferroni method to determine which pairs of means, if any, are different at the 5% level.

b. Use the Tukey-Kramer method to determine which pairs of means, if any, are different at the 5% level.

c. Which is the more powerful method to find all the pairs of treatments whose means are different, the Bonferroni method or the Tukey-Kramer method?

Groups Randomize control group Split individuals into two groups separately Control vs. treatment Compare the two averages correlation between the groups (Measure the strength before and after to get the experiment) Matching Observed and match into pairs with two treatments (Longitudinal and measures) Each group has their own control group within Find the change between the strength and average added between both old and new Compute: d= x1x2 X1= response from one event X2= response from another event Analyzing D is what the gain and strength is Next: one variable to look over Find dbar and Sd After: use dbar and Sd to inference about Mud (Standard deviation of differences) To what value should we compare dbar Ho: Mud= 0 does