A company that employs a large number of salespeople is interested in determining which of the following subsets of the sales staff sells, on average, the most: (1) those whose compensation consists of a fixed salary, (2) those whose compensation is based strictly on commission, and (3) those whose compensation is based on a smaller fixed portion and a reduced commission rate. Sales data (in dollars) from the previous quarter are collected for randomly selected salespeople who are compensated according to one of the three aforementioned schemes. The data are given in the file P12_11.XLS. 

a. Is there any reason to doubt the equal-variance assumption made in the one-way ANOVA model in this particular case? Support your response to this question. 

b. Can you reject at the 5% significance level that the mean sales are the same for each of the three groups of salespeople? Explain why or why not. 

c. Generate 95% confidence intervals for all pairs of differences between means. Which of these differences, if any, are statistically significant at the 5% significance level?