The Softball data file on the text CD contains the records of a University of Georgia coed intramural softball team for 277 games over a 20-year period. (The players changed, but the team continued.) The variables include, for each game, the team’s number of runs scored (RUNS), number of hits (HIT), number of errors (ERR), and the difference (DIFF) between the number of runs scored by the team and by the other team. Let DIFF be the response variable. DIFF 7 0 means the team won and DIFF 6 0 means the team lost.
a. Construct a modified box-plot of DIFF. What do the three outlying observations represent?
b. Find the prediction equation relating DIFF to RUNS. Show that the team is predicted to win when RUNS = 8 or more.
c. Construct the correlation matrix for RUNS, HIT, ERR, and DIFF, and interpret.
d. Conduct statistical inference about the slope of the relationship between DIFF and RUNS.