1. Consumer spending. An analyst at a large credit card bank is looking at the relationship between customers' charges to the bank's card in two successive months. He selects 150 customers at random, regresses charges in March ($) on charges in February ($), and finds an R2 of 79%. The intercept is $730.20, and the slope is 0.79. After verifying all the data with the company's CPA, he con- cludes that the model is a useful one for predicting one month's charges from the other. Examine the data on the CD and comment on his conclusions.
2. Insurance policies. An actuary at a mid-sized insurance company is examining the sales performance of the com- pany's sales force. She has data on the average size of the policy ($) written in two consecutive years by 200 sales- people. She fits a linear model and finds the slope to be 3.00 and the R2 is 99.92%. She concludes that the predictions for next year's policy size will be very accurate. Examine the data on the CD and comment on her conclusions.
3. What slope? If you create a regression model for pre- dicting the sales ($ million) from money spent on advertis- ing the prior month ($ thousand), is the slope most likely to be 0.03, 300 or 3000? Explain.