Suppose we asked a group of participants whether they liked Monday Night Football, then made them watch a game and asked them again. Our interest lies in whether watching a game changes people’s opinions. Out of 80 participants, 20 changed their opinion from Favorable to Unfavorable, while 5 changed from Unfavorable to Favorable. (The others did not change.) Did watching the game have a systematic effect on opinion change? [This test on changes is the test suggested by McNemar (1969).]

a. Run the test.

b. Explain how this tests the null hypothesis.

c. In this situation the test does not answer our question of whether watching football has a serious effect on opinion change. Why not?