solution

a. What other nonparametric test could you have used to analyze the data presented in Problem 15?

b. Use this test to analyze the data. What do you conclude with  0.051_tail?

c. Explain the difference between your conclusions for Problems 16b and 15c.

d. Let P equal the probability for each subject that diet plus exercise will yield greater weight loss. If Preal 0.75, using the sign test with  0.051_tail, what is the power of the experiment to detect this level of effect? What is the probability of making a Type II error? Health

Problem 15

A study is conducted to determine whether dieting plus exercise is more effective i n producing weight loss t hand ieting alone. Twelve pairs o f matched subjects are run in t he study. Subjects are matched on initial weight, initial level o f exercise, age, and gender. One member of each pair is put on a diet for 3 months. The other member receives the same diet but, in addition, is put on a moderate exercise regimen. The following scores indicate the weight loss in pounds over the 3-month period for each subject:

In answering t he following questions, assume t he data are very nonnormal so as to preclude using the appropriate parametric test.

a. What is t he a lternative hypothesis? Use a d irectional hypothesis.

b. What is the null hypothesis?

c. Using  0.051 tail, what do you conclude? Health

Problems 16b

b. Use this test to analyze the data. What do you conclude with  0.051_tail?

Problems 15c

c. Using  0.051 tail, what do you conclude? Health