Question:
When a popular music artist dies, sales of the artist's albums often increase dramatically. A study of the effect of after-death publicity on album sales was published in Marketing Letters (March 2016). The following data were collected weekly for each of 446 albums of artists who died a natural death: album publicity (measured as the total number of printed articles in which the album was mentioned at least once during the week), artist death status (before or after death), and album sales (dollars). Suppose you want to use the data to model weekly album sales (y) as a function of album publicity and artist death status. Do you recommend using stepwise regression to find the "best" model for predicting y? Explain. If not, outline a strategy for finding the best model.
Transcribed Image Text:
Variables Entered Removed Variables Removed Variables Model Entered Method Stepwise (Criteria Probabity-of-F-to-enter <= 050, Probability-of-F-to-remove >.100). ST DEPTH Stepwise (Criteria. Probability-of-F-to-enter 050, Probability-of-F-to-remove > 100). Stepwise (Criteria: Probability-of-F-to-enter < 050, Probability-of-F-to-remove > 100). TGRSWT TI a. Dependent Variable: LOGNUM Model Summary Std. Error of the Estimate 7615773 Adjusted R Square RSquare 121 Model 329 122 427 432 a. Predictors: (Constart), ST_DEPTH b. Predictors: (Constant), ST DEPTH, TGRSWT C. Predictors: (Constant), ST_DEPTH, TGRSWT, TI .182 187 .180 184 7348470 7346469