I asked you to imagine that I worked for a record company and that my boss was interested in predicting record sales from advertising. Before a record is released, the executive notes the amount spent on advertising, the number of times the record is played on radio the week before release, and the attractiveness of the band. He does this for 200 different records (each made by a different band). Attractiveness was measured by asking a random sample of the target audience to rate the attractiveness of each band on a scale from 0 (hideous potato-heads) to 10 (gorgeous sex objects). The mode attractiveness given by the sample was used in the regression (because he was interested in what the majority of people thought, rather than the average of people's opinions).

Copy and paste the data below into SPSS. (note the data appear out of line but they are tab delimited for easy pasting into spss). Make sure after you paste the variables into spss that they all remain scale and numeric (see data view)

Model Summary Adjusted R Std. Error of Model R R Square Square the Estimate 815 665 660 47.08735 a. Predictors: (Constant), Attract, Adverts, Airplay ANOVA Sum of Model Squares df Mean Square F Sig Regression 861377.220 3 287125.740 129.498 Residual 434574.780 196 2217.218 Total 1295952.000 199 a. Dependent Variable: Sales b. Predictors: (Constant), Attract, Adverts, Airplay Coefficients Standardized Unstandardized Coefficients Coefficients 95.0% Confidence Interval for B Model B Std. Error Beta Sig. Lower Bound Upper Bound (Constant) -26.613 17.350 1.534 127 -60.830 7.604 Adverts 085 .007 511 12.261 000 071 099 Airplay 3.367 278 512 12.123 000 2.820 3.915 Attract 11.086 2.438 192 4.548 000 6.279 15.894 a. Dependent Variable: Sales O