Question

Assume a manager wants to know if exposure to a new tv advertisement improves attitudes toward the brand. She hires an ad copy testing firm to conduct a test. 200 randomly selected potential customers are paid to participate. Half of the sample is assigned to a watch a brief TV show segment in which there is an ad pod containing the firm’s new ad. The other half of the sample is assigned to watch the same TV segment, but the firm’s ad is not in the ad pod. After exposure, attitudes toward the brand are measured for each group, those exposed to the ad and those not exposed. In the ad-exposure group, the average brand attitude was 5.3. In the non-exposure group, the average brand attitude was 5.0. What would be the appropriate statistical test to determine whether or not the ad really works??
A. Chi-square analysis
B. Test of a single mean (one-sample t-test)
C. Paired samples t-test

D. Independent samples t-test

Answer 1

We are basically dividing the smaple into two independent groups and then testing for the Difference in mean. So,

Independent samples t test should be used.