11.1 Consider the regression model developed for the National Football League data in Problem 3.1. a. Calculate the PRESS statistic for this model. What comments can you make about the likely predictive performance of this model? b. Delete half the observations (chosen at random), and refit the regression model. Have the regression coefficients changed dramatically? How well does this model predict the number of games won for the deleted observations? y x1 x2 x3 x4 x5 x6 x7 x8 x9 10 2113 1985 38.9 64.7 11 2957 1737 40.1 60 13 2285 2905 41.6 45.3 10 2971 1666 39.2 53.8 15 4445 868 59.7 2205 1917 914 65.6 1847 2175 957 61.4 1903 2476 836 66.1 1457 1866 11 2309 2927 39.7 74.1 8 786 61 1848 2339 11 2147 2737 37 78.3 4 1689 1414 42.1 47.6 2 2566 1838 42.3 54.2 10 2109 2191 39.5 51.9 9 2295 2229 37.4 53.6 9 1932 2204 35.1 71.4 3 10 5 1722 1730 36.6 52.6 -19 4346 539 -1 761 58 1821 1909 -3 714 57 2577 2001 -1 797 58.9 2476 2254 700 57.2 1917 1758 -5 1037 58.8 1761 2032 986 58.6 1709 2025 791 54.4 2288 1835 564 1873 2929 41.1 55.3 10 789 54.3 2861 2496 2118 2268 38.2 69.6 6 582 58.7 2411 2670 1775 1983 39.3 78.3 7 901 51.7 2289 2202 3 1929 1606 39.7 68.8 -21 3 4682 2080 1492 35.5 68.8 2040 2416 38.7 50 2447 1638 39.9 57.1 7808 627 52.7 2592 2324 -8 722 57.8 2053 2550 576 54.9 2048 2628 -8 848 65.3 1786 1776 1416 2649 37.4 56.3 -22 684 43.8 2876 2524