52. Refer to Problem 7 10 Suppose the same 1600 people who were interviewed in January were interviewed again in February. with the results shown in Table 7.21 TABLE 7.21 February January Approve Disapprove Total Approve 794 86 880 Disapprove Total 150 570 720 944 656 1600

a) Test for a difference between the proportions who approve in February and in January. Interpret

b) Find a 95% confidence interval for the difference between the proportions who approve in February and in January. Interpret. Can you conclude that the approval rating changed from January to February? Explain.

c) Compare results to those in Problem 7 10 for the independent samples. In particular. compare the standard error for the difference of proportions for the two analyses. How does this affect the width of the confidence interval? Which analysis provides more pre- cise results and why does this happen?