# 1. All the coefficients of the dummy variables in Jame's regression are negative except that for Nov. Does this make sense? Explain. 2. Are you happy with Jame's regression model? What changes would you make, if any? 3. Using Jame's fitted model in Table 8-23, generate forecasts for the remaining seven months of 2003. 4. Fit an autoregressive model to

1. All the coefficients of the dummy variables in Jame's regression are negative except that for Nov. Does this make sense? Explain.

2. Are you happy with Jame's regression model? What changes would you make, if any?

3. Using Jame's fitted model in Table 8-23, generate forecasts for the remaining seven months of 2003.

2. Are you happy with Jame's regression model? What changes would you make, if any?

3. Using Jame's fitted model in Table 8-23, generate forecasts for the remaining seven months of 2003.

4. Fit an autoregressive model to Jame's data with sales lagged 12 months as the predictor variable. Is this model reasonable? Generate forecasts for the remaining seven months of 2003 using your autoregressive model.

5. Which model, the dummy variable regression orthe autoregression, do you prefer? Why?

Jame Luna's efforts to understand the trend and seasonality in Surtido Cookies monthly sales have been examined in Cases 3-5, 4-8, and 5-7. The fact that cookie sales are seasonal is now well established. Jame and his team have tried a smoothing procedure, decomposition, and now are interested in trying regression methods in their continuing attempt to come up with a procedure that produces the "best" forecasts of future sales.

## This problem has been solved!

Do you need an answer to a question different from the above? Ask your question!

**Related Book For**