The file P10_08.xlsx contains data on the top 200 professional golfers in each of the years 2003–2009.
a. Create one large data set in a new sheet called All Years that has the data for all seven years stacked on top of one other. In this combined data set, create a new column called Earnings per Round, the ratio of Earnings to Rounds. Similarly, create three other new variables, Eagles per Round, Birdies per Round, and Bogies per Round.
b. Using the data set from part a, run a forward regression of Earnings per Round versus the following potential explanatory variables: Age, Yard/Drive, Driving Accuracy, Greens in Regulation, Putting Average, Sand Save Pct, Eagles per Round, Birdies per Round, and Bogies per Round. Given the results, comment on what seems to be important on the professional tour in terms of earnings per round. For any variable that does not end up in the equation, is it omitted because it is not related to Earnings per Round or because its effect is explained by other variables in the equation?
c. Repeat part b with backward regression. Do you get the same, or basically the same, results?