NBA Statistical Analysis Econ 240A Group Project II 12 3 08 Jeff Lee Zhen Tian Tsung Ching Huang Oystein Tennum Christian Treubig Eddie Bedach Analysis Method Statistics Collected Salary Dependent Variable Height Weight PPG RPG APG SPG BPG All Star Status Number of teams played for Analysis Method 300 player database created 50 players from each division Starters and Second string from each team Exploratory Data Analysis Investigation of various factors on salary Ordinary Least Square T statistic F statistic Analysis of Variance Physical Attributes Dependent Variable SALARY Height and weight found to be insignificant Method Least Squares Tall Weak is undesirable Short Strong is undesirable U re shorter yet fatter Sample 1 300 Included observations 300 Variable Coefficient HEIGHT 151029 1 WEIGHT 16999 88 C 9864304 R squared 0 041654 Std Error t Statistic 103165 2 1 463954 14633 30 1 161726 6208414 1 588861 Mean dependent var Prob 0 1443 0 2463 0 1132 5911743 Adjusted R squared 0 035223 S D dependent var 5018847 S E of regression 4929667 Akaike info criterion 33 66936 Sum squared resid Why I was picked after you 7 24E 15 Schwarz criterion 33 70631 Log likelihood 5064 238 F statistic 6 476267 Durbin Watson stat 1 925366 Prob F statistic 0 001765 Physical Attributes Created dummy variable Body height weight Body was found to be significant Dependent Variable SALARY Method Least Squares Sample 1 300 Included observations 300 Variable Coefficient Std Error t Statistic Prob BODY 338 0742 94 68063 3 570680 0 0004 C 101890 1 1707911 0 059658 0 9525 R squared 0 040897 Mean dependent var 5911743 Adjusted R squared 0 037690 S D dependent var 5018847 S E of regression 4923359 Akaike info criterion 33 66350 Sum squared resid 7 25E 15 Schwarz criterion 33 68813 Log likelihood 5064 357 F statistic 12 74976 Prob F statistic 0 000415 Durbin Watson stat 1 933402 Statistical Performance Dependent Variable SALARY Method Least Squares Most Important Factors 1 Blocks 2 Assists 3 Points 4 Rebounds 5 Steals Sample 1 300 Included observations 300 Variable Coefficient Std Error t Statistic Prob APG 541720 3 159737 9 3 391307 0 0008 BPG 1727532 488891 3 3 533571 0 0005 PPG 502778 7 52958 75 9 493781 0 0000 RPG 424591 4 130701 2 3 248565 0 0013 SPG 549798 2 664644 0 0 827207 0 4088 C 2748804 465895 7 5 900042 0 0000 R squared 0 641952 Mean dependent var 5911743 Adjusted R squared 0 635883 S D dependent var 5018847 S E of regression 3028477 Akaike info criterion 32 70475 Sum squared resid 2 71E 15 Schwarz criterion 32 77865 Log likelihood 4916 065 F statistic 105 7824 Prob F statistic 0 000000 Durbin Watson stat 1 682747 Defense Wins Championships To investigate this two dummy variables were created OFFENSE PPG APG DEFENSE RPG BPG SPG Defense was found to be much more Dependent Variable SALARY Method Least Squares Sample 1 300 Included observations 300 Variable Coefficient Std Error t Statistic Prob DEFENSE OFFENSE C 511695 3 78918 61 2453181 43166 52 6159 982 266479 8 11 85399 12 81150 9 205881 0 0000 0 0000 0 0000 significant Teams are willing to pay more for defensive stars R squared Adjusted R squared S E of regression Sum squared resid Log likelihood F statistic Prob F statistic 0 553566 0 550570 3364611 3 37E 15 4949 269 184 7563 0 000000 Mean dependent var S D dependent var Akaike info criterion Schwarz criterion Hannan Quinn criter Durbin Watson stat 5911743 5018847 32 90544 32 94239 32 92022 1 953691 All Star Status Highly Significant All Stars make over an average of 3 426 702 more than non all star players Dependent Variable SALARY Method Least Squares Sample 1 300 Included observations 300 Variable Coefficient ALLSTAR 3426702 APG 462621 4 BPG 1223729 PPG 363983 5 RPG 425565 1 SPG 569773 6 C 1448944 R squared 0 675249 Adjusted R squared 0 668622 S E of regression 2889123 Sum squared resid 2 45E 15 Log likelihood 4901 375 Durbin Watson stat 1 727203 Std Error t Statistic 624127 2 5 490390 153067 2 3 022343 475336 2 2 574450 56493 55 6 442921 124687 2 3 413062 634071 1 0 898596 503581 2 2 877281 Mean dependent var S D dependent var Akaike info criterion Schwarz criterion F statistic Prob F statistic Prob 0 0000 0 0027 0 0105 0 0000 0 0007 0 3696 0 0043 5911743 5018847 32 61378 32 70000 101 8850 0 000000 All Star Non All Star Difference Why I earn much less than u 5 Yrs for 50 000 000 6 Yrs for 118 000 000 16 1 points game 16 8 points game 5 1 rebounds game 5 8 rebounds game 2 2 assists game 1 8 assists game 9 Years for 3 Teams 10 Years for 2 Team 78 inches 225 lbs 82 inches 230 lbs All Star No All Star Yes only 2005 Franchise Player A player who plays for one team for the majority of his career is considered a Franchise Player Create a dummy variable FRANCHISEVET Product of Variables Franchise and Veteran Franchise 1 if player has played for one team only Veteran 1 if Years Played 5 Franchise Players make nearly 3 million more per year on average Dependent Variable SALARY Method Least Squares Sample 1 300 Included observations 300 Variable Coefficient Std Error t Statistic Prob FRANCHISEVET 2997136 774263 4 3 870952 0 0001 APG 554151 9 156114 3 3 549654 0 0004 BPG 1463554 482542 9 3 033003 0 0026 PPG 471283 8 52382 18 8 997027 0 0000 RPG 432064 7 127723 9 3 382803 0 0008 SPG 411064 2 650417 5 0 632001 0 5279 C 2616565 456510 7 5 731662 0 0000 R squared 0 659316 Mean dependent var 5911743 Adjusted R squared 0 652363 S D dependent var 5018847 S E of regression 2959150 Akaike info criterion 32 66168 Sum squared resid 2 57E 15 Schwarz criterion 32 74790 Log likelihood 4908 583 F statistic 94 82814 Prob F statistic 0 000000 Durbin Watson stat 1 604668 Larry Bird Rule Exceed the salary cap to re sign their free agents Up to maximum salary Money Money Go My Home Up to 6 Years in Length Play 3 seasons without waived or traded as a free agent Linear Regression Dependent Variable SALARY Method Least Squares Sample 1 301 Included observations 301 Variable Coefficient TEAM YEARS C R squared Adjusted R squared S E of regression Sum squared resid Log likelihood F statistic Prob F statistic 1641837 1243723 3018149 0 507669 0 504365 3533337 3 72E 15 4963 997 153 6418 0 000000 Std Error t Statistic Prob 157925 7 71014 20 376357 8 10 39626 17 51373 8 019361 0 0000 0 0000 0 0000 Mean dependent var S D dependent var Akaike info criterion Schwarz criterion Hannan Quinn criter Durbin Watson stat 5911743 5018847 33 00330 33 04025 33 01809 2 059176 Two Factor Anova Yr3 Yr4 Yr5 Yr6 Yr7 Yr8 Yr9 Yr10 Yr11 Yr12 Team1 2329805
View Full Document
Unlocking...