1. Using the data in Table 8-21 and the independent variables described in Case 7-2, which regression model is the best for prediction? Are the signs on the coefficients for the independent variables what you would expect them to be? Are the coefficients of the independent variables significantly different from zero?

2. Is serial correlation a problem? If any coefficients are not significantly different from zero, try running a regression without these independent variables. Try experimenting with different powers for the exponential transformation.
3. Prepare a memo to Michael recommending the regression model you believe is more appropriate for predicting the cyclical nature of emergency road service call volume.
An overview of AAA Washington was provided in Case 5-5 when students were asked to prepare a time series decomposition of the emergency road service calls received by the club over five years. The time series decomposition performed in Case 5-5 showed that the pattern Michael DeCoria had observed in emergency road service call volume was probably cyclical in nature. Michael wanted to be able to predict the cyclical effect on emergency road service call volume for future years.

Transcribed Image Text:

TABLE 8-21 (Continued) Year Mth Calls Unemployment Rate Temperature Rainfall Members 2.12 450,001 161 452.303 05 456,551 2.80 455,747 19,077 19,141 20,883 August 20.709 September 19.647 October 22013 November 22,375 December 22.727 1992 January 22367 February 21.155 March 21.209 19.286 5.8146 5.9480 5.9026 5.7227 June 7.0615 7.4370 8.4513 8,7699 8.0728 7.2392 7.0461 7.0478 7.1080 6.7824 6.7691 5896 7.9908 8.2460 1.70 462,340 6.50 460.492 3.45 465361 7.26 465,492 3.59 466,775 1.47 467,168 4.35 464 575 0.60 459,019 1.84 463,665 141 463,775 1.01 466,230 May June 64.9 20.795 August 21.126 September 20.251 October 22,069 November 23.268 December 26,039 1993 January 26,127 February 20,067 March 19.673 19,142 4.38 9.2790 8.6802 7.7815 7.4338 7.3701 7.2442 May June Data not available