The following situations all require inference about a population mean or means. Identify the design of each study as one that would require either a single sample t procedure, a matched pairs (dependent) sample t procedure, or a two independent samples t procedure.

a. You place an SRS of people on a diet for eight weeks and for each person you compute the weight lost over the eight-week period by subtracting their weight at the beginning of the study from their weight at the end of the eight-week period. You estimate the mean weight loss using a 95% confidence interval.

b. You own a retail business and there is an SRS survey of your customers every year. One of the questions on the survey asks about customer satisfaction on a seven-point scale with the response 1 indicating "very dissatisfied" and 7 indicating "very satisfied." You want to see if the mean customer satisfaction has improved from last year.

c. The consumer advocacy group you work for asks you to take an SRS of a certain make of car in order to test a claim made by the manufacturer. The manufacturer claims that this particular make of automobile will on average get 40 miles per gallon. You want to test their claim by driving the cars in your sample through a course designed to simulate typical driving conditions. You will use the mean miles per gallon for your sample of cars to test the manufacturer's claim.