Computer Rating System Prediction Results for College Football (NCAA IA)
2011 Retrodiction Results
Through
| Rank |
System |
Pct. Correct |
Against Spread |
Absolute Error |
Bias |
Mean Square Error |
games |
suw |
sul |
atsw |
atsl |
| 1 | CPA Retro | 0.87832 | 0.00000 | 11.8004 | -3.6877 | 240.229 | 715 | 628 | 87 | 0 | 0 |
| 2 | Least Squares w/ HFA | 0.84755 | 0.00000 | 9.0689 | -0.0959 | 125.484 | 715 | 606 | 109 | 0 | 0 |
| 3 | Sagarin Elo | 0.84755 | 0.00000 | 11.0196 | -1.1574 | 205.363 | 715 | 606 | 109 | 0 | 0 |
| 4 | Martien Maas | 0.84755 | 0.00000 | 14.4107 | 1.3510 | 330.588 | 715 | 606 | 109 | 0 | 0 |
| 5 | Wolfe * | 0.84615 | 0.00000 | 10.9916 | -0.0383 | 202.142 | 715 | 605 | 110 | 0 | 0 |
| 6 | SuperList | 0.84476 | 0.00000 | 11.9922 | 0.2561 | 234.785 | 715 | 604 | 111 | 0 | 0 |
| 7 | Colley Rankings * | 0.84056 | 0.00000 | 11.0983 | -0.1241 | 204.094 | 715 | 601 | 114 | 0 | 0 |
| 8 | Logistic Regression | 0.84056 | 0.00000 | 14.3664 | -4.5318 | 352.290 | 715 | 601 | 114 | 0 | 0 |
| 9 | Massey Concensus Rank | 0.83636 | 0.00000 | 10.8904 | -0.0081 | 196.285 | 715 | 598 | 117 | 0 | 0 |
| 10 | Anderson/Hester * | 0.83497 | 0.00000 | 11.1173 | -0.0280 | 203.600 | 715 | 597 | 118 | 0 | 0 |
| 11 | Warren Claassen | 0.83217 | 0.00000 | 10.5500 | -0.6229 | 187.727 | 715 | 595 | 120 | 0 | 0 |
| 12 | Beck Elo | 0.83077 | 0.00000 | 10.5775 | -0.9343 | 190.245 | 715 | 594 | 121 | 0 | 0 |
| 13 | Sagarin | 0.82797 | 0.00000 | 10.3277 | -0.6716 | 176.448 | 715 | 592 | 123 | 0 | 0 |
| 14 | system Median | 0.82657 | 0.00000 | 10.1313 | -0.5344 | 172.265 | 715 | 591 | 124 | 0 | 0 |
| 15 | System Average | 0.82657 | 0.00000 | 10.1646 | -0.4943 | 172.341 | 715 | 591 | 124 | 0 | 0 |
| 16 | NutShell Combo | 0.82238 | 0.00000 | 11.4410 | -0.7902 | 222.310 | 715 | 588 | 127 | 0 | 0 |
| 17 | Schmidt Comp. Ratings | 0.82238 | 0.00000 | 10.8868 | -0.9138 | 199.224 | 715 | 588 | 127 | 0 | 0 |
| 18 | Sonny Moore | 0.81958 | 0.00000 | 10.4300 | -0.2925 | 180.878 | 715 | 586 | 129 | 0 | 0 |
| 19 | Least Squares | 0.81538 | 0.00000 | 10.0003 | -0.0703 | 162.240 | 715 | 583 | 132 | 0 | 0 |
| 20 | Payne Power Ratings | 0.81538 | 0.00000 | 10.0306 | 0.1692 | 163.329 | 715 | 583 | 132 | 0 | 0 |
| 21 | Born Power Index | 0.81399 | 0.00000 | 10.3783 | 0.0572 | 176.998 | 715 | 582 | 133 | 0 | 0 |
| 22 | Laz Index | 0.81259 | 0.00000 | 10.4030 | -0.6598 | 178.396 | 715 | 581 | 134 | 0 | 0 |
| 23 | Edward Kambour | 0.80839 | 0.00000 | 10.0700 | -0.2155 | 164.797 | 715 | 578 | 137 | 0 | 0 |
| 24 | Nutshell Girl | 0.80839 | 0.00000 | 12.7131 | -1.2264 | 271.411 | 715 | 578 | 137 | 0 | 0 |
| 25 | Covers.com | 0.80280 | 0.00000 | 11.0976 | -0.6375 | 208.976 | 715 | 574 | 141 | 0 | 0 |
| 26 | NutShell Sports | 0.80280 | 0.00000 | 10.8278 | -0.3539 | 200.218 | 715 | 574 | 141 | 0 | 0 |
| 27 | Sagarin Predictive | 0.80280 | 0.00000 | 10.1621 | -0.7726 | 169.056 | 715 | 574 | 141 | 0 | 0 |
| 28 | CPA Rankings | 0.80280 | 0.00000 | 10.0829 | 0.1559 | 165.361 | 715 | 574 | 141 | 0 | 0 |
| 29 | Stat Fox | 0.79161 | 0.00000 | 10.3888 | 0.6542 | 174.304 | 715 | 566 | 149 | 0 | 0 |
| 30 | Stortrends | 0.77557 | 0.00000 | 10.9034 | -1.3166 | 186.602 | 704 | 546 | 158 | 0 | 0 |
| 31 | PerformanZ Ratings | 0.77483 | 0.00000 | 10.9577 | -0.2971 | 189.255 | 715 | 554 | 161 | 0 | 0 |
| 32 | Pigskin Index | 0.77483 | 0.00000 | 11.3007 | -0.2712 | 213.158 | 715 | 554 | 161 | 0 | 0 |
| 33 | Stephen Kerns | 0.75745 | 0.00000 | 10.8453 | -0.7782 | 173.378 | 705 | 534 | 171 | 0 | 0 |
* This system does not make predictions. I make predictions for this
system by translating it to a new scale that allows for making predictions.
Retrodictive records are found by taking the ratings from the current week
and applying them to the entire season to date.
The ideal system would be one that has the highest correct game decisions,
has the smallest mean error(deviation from the actual game result), and has
a bias of zero.
Mean Error = average[abs(prediction-actual)]
Bias = agerage(prediction - actual)
Std. = Standard Deviation of individual game biases