1. Analyze the significance of the variables in Dorothy's regression model. Develop a regression model (be sure to include additive dummy variables for the seasonal component, if necessary), and use it to forecast the number of new clients for the first three months of 1993. Compare your forecasts with the actual observations.
2. Develop an autoregressive model, and generate forecasts for the first three months of 1993. Which model (multiple regression or autoregression) do you feel is the better candidate for generating forecasts for the rest of 1993? Write Dorothy a memo that provides her with the information she has requested concerning the problem of serial correlation. Include an analysis of the results of your efforts to develop an appropriate model to forecast the number of new clients for the remainder of 1993.
The Consumer Credit Counseling (CCC) operation was described in Cases 1-2 and 3-3.
The executive director, Marv Harnishfeger, concluded that the most important variable that CCC needed to forecast was the number of new clients to be seen in the rest of 1993. Marv provided Dorothy Mercer monthly data for the number of new clients seen by CCC for the period from January 1985 through March 1993 (see Case 3-3). In Case 3-3, Dorothy used autocorrelation analysis to explore the data pattern. In Case 6-5, she tried both the number of people on food stamps and a business activity index to develop a regression model to forecast the rest of 1993.