A cola-tasting experiment is conducted in which 100 people are each given a half-cup of Cola A and a half-cup of Cola B. All 100 participants taste both colas and then rate the taste of each cola on a 0 (horrible) to 50 (tastes great) scale. For each person, a coin is tossed to determine the order of tasting the two colas. To estimate the mean difference between ratings of the two products, what procedure should be used?
A) A confidence interval for one proportion.
B) A confidence interval for a difference between two proportions.
C) A paired t (or 1-sample t) confidence interval for a mean difference.
D) A 2-sample t confidence interval for a difference in two means.

Question

Quizplus · Accepted Answer

Since each participant tastes both colas and provides a rating for each, the ratings for Cola A and Cola B are paired data for each participant. The appropriate procedure to estimate the mean difference between the paired ratings is a paired t (or 1-sample t) confidence interval for a mean difference.

A Cola-Tasting Experiment Is Conducted in Which 100 People Are