The file P14_21.xlsx contains data on over 200 movies that came out in 2006 and 2007. Create a new variable Total Revenue that is the sum of Total US Gross, International Gross, and US DVD Sales. How well can this new variable be predicted from the data in columns C–F? For Distributor, relabel the categories so that there are only two: Large Distributor and Small Distributor.

The former is any distributor that had at least 12 movies in this period, and the latter is all the rest.

For Genre, relabel the categories to be Comedy, Drama, Adventure, Action, Thriller/Suspense, and Other. (Other includes Black Comedy, Documentary, Horror, Musical, and Romantic Comedy.) Interpret the coefficients of the estimated regression equation. How would you explain the results to someone in the movie business? Do you think that predictions of total revenue from this regression equation will be very accurate? Why?