Five treatments for fever blisters, including a placebo, were randomly assigned to 30 patients. For each of

Question:

Five treatments for fever blisters, including a placebo, were randomly assigned to 30 patients. For each of the five treatments, the data in the accompanying table identify the number of days from initial appearance of the blisters until healing is complete.

Treatment No. of Days

Placebo (1) ………… 5, 8, 7, 7, 10, 8

2 …………………………. 4, 6, 6, 3, 5, 6

3 …………………………. 6, 4, 4, 5, 4, 3

4 …………………………. 7, 4, 6, 6, 3, 5

5 …………………………. 9, 3, 5, 7, 7, 6

a. Compute the sample means and the sample standard deviations for each treatment.

b. Complete the ANOVA table in the accompanying computer output for the data given.

c. Do the effects of the five treatments differ significantly with regard to healing fever blisters? In other words, test H₀: µ₁ = µ₂ = µ₃ = µ₄ = µ₅ against H_A: "At least two treatments have different population means."

d. What are the estimates of the true effects (µ_i - µ) of the treatments? Verify that the sum of these estimated effects is 0.

e. Using dummy variables, create an appropriate regression model that describes this experiment. Give two possible ways of defining these dummy variables (one using 0's and 1 's and the other using 1 's and - l's), and describe for each coding scheme how the regression coefficients are related to the population means µ₁, µ₂, µ₃, µ₄, µ₅, and µ.

f. For the data of this problem, carry out the Scheffe, Tukey-Kramer, and Bonferroni multiple-comparison procedures for examining pairwise differences between means, as described in Section 17.7. Also, compare the widths of the confidence intervals obtained by the three procedures.

Dependent Variable: days