In the book Essentials of Marketing Research, William R. Dillon, Thomas J. Madden, and Neil H. Firtle (1993) present pre-exposure and post-exposure attitude scores from an advertising study involving 10 respondents. The data can be found on our Excel worksheet. Assuming that the differences between pairs of post-exposure and pre-exposure scores are Normally distributed:

a) State the null and alternative hypotheses needed to attempt to establish that the advertisement increases the mean attitude score (that is, that the mean post-exposure attitude score is higher than the mean pre-exposure attitude score).

b) Test this hypothesis at α=.01 What is your conclusion?

c) Test this hypothesis at α=.001 What is your conclusion?

d) Is there a difference in your conclusions for parts b. and c.? If so, why does this difference exist?