Effect of partner smoking in smoking cessation study Smokers may have a more difficult time quitting smoking if they live with a smoker. How can an experiment explore this possibility in a study to compare bupropion with placebo? Suppose the researchers split the subjects into two groups: those who live with a smoker and those who do not live with smokers. Within each group, the subjects are randomly assigned to take bupropion or a placebo. The figure shows a flow chart of this design, when 250 of the 429 study subjects live with nonsmokers and 179 live with a smoker.

a. Is this design a completely randomized design? Why or why not? (Hint: Is the smoking status of the person a subject lives with randomly determined?)

b. Does this experiment have blocks? If so, identify them.

c. Is this design a randomized block design? Explain why or why not.

Transcribed Image Text:

Experimental Units: 429 Smokers Block the subjects according to whether they live with a smoker. Block 1 Block 2 Does Not Live with Smoker Lives with Smoker (n=250) Randomly assign to a treatment group. (n=179) Randomly assign to a treatment group. Treatment 1 Treatment 2 Treatment 1 Bupropion Placebo Bupropion (90 subjects) (125 subjects) (125 subjects) Compare the two treatment percentages of those who have relapsed. Treatment 2 Placebo (89 subjects) Compare the two treatment percentages of those who have relapsed.