Refer to Table 6.3. Viewing the table as matched triplets, one can compare the proportion of "yes" responses among the three drugs.

a. Construct the marginal distribution for each drug, and compute the three sample proportions of "yes" responses.

b. Representing the data with a 32 partial table of drug-by-response for each subject, use a generalized CMH procedure (Cochran's Q) to test marginal homogeneity.

c. Repeat the test after eliminating the 911 + 279 subjects who make the same response for every drug. What effect do such observations have on the test?