Computer Rating System Prediction Results for College Football (NCAA IA)
2010 Retrodiction Results
Through
| Rank |
System |
Pct. Correct |
Against Spread |
Absolute Error |
Bias |
Mean Square Error |
games |
suw |
sul |
atsw |
atsl |
| 1 | Warren Claassen | 0.96667 | 0.00000 | 8.9121 | 1.1987 | 132.127 | 180 | 174 | 6 | 0 | 0 |
| 2 | Sagarin Elo | 0.95000 | 0.00000 | 9.6536 | 0.8747 | 163.660 | 180 | 171 | 9 | 0 | 0 |
| 3 | Beck Elo | 0.93889 | 0.00000 | 7.2385 | -0.5230 | 104.428 | 180 | 169 | 11 | 0 | 0 |
| 4 | Massey Concensus Rank | 0.93889 | 0.00000 | 8.3462 | 1.0293 | 126.470 | 180 | 169 | 11 | 0 | 0 |
| 5 | Sagarin | 0.92222 | 0.00000 | 8.4360 | 0.3002 | 127.337 | 180 | 166 | 14 | 0 | 0 |
| 6 | SuperList | 0.91667 | 0.00000 | 10.3323 | 2.3872 | 174.264 | 180 | 165 | 15 | 0 | 0 |
| 7 | Payne Power Ratings | 0.91111 | 0.00000 | 6.3483 | -0.0133 | 70.910 | 180 | 164 | 16 | 0 | 0 |
| 8 | Nutshell Girl | 0.89444 | 0.00000 | 11.4693 | -1.0651 | 233.316 | 180 | 161 | 19 | 0 | 0 |
| 9 | Schmidt Comp. Ratings | 0.89266 | 0.00000 | 8.4863 | -0.8907 | 134.910 | 177 | 158 | 19 | 0 | 0 |
| 10 | System Average | 0.88889 | 0.00000 | 7.9951 | 0.1266 | 114.604 | 180 | 160 | 20 | 0 | 0 |
| 11 | system Median | 0.87222 | 0.00000 | 7.9170 | 0.0246 | 113.815 | 180 | 157 | 23 | 0 | 0 |
| 12 | Covers.com | 0.86667 | 0.00000 | 9.3258 | 0.9197 | 162.089 | 180 | 156 | 24 | 0 | 0 |
| 13 | Pigskin Index | 0.86111 | 0.00000 | 8.4944 | 0.7167 | 126.203 | 180 | 155 | 25 | 0 | 0 |
| 14 | DP Dwiggins | 0.86111 | 0.00000 | 8.4653 | -3.1108 | 118.154 | 180 | 155 | 25 | 0 | 0 |
| 15 | NutShell Combo | 0.85556 | 0.00000 | 9.8983 | 1.0034 | 177.002 | 180 | 154 | 26 | 0 | 0 |
| 16 | Edward Kambour | 0.85000 | 0.00000 | 7.7556 | 0.2651 | 100.780 | 180 | 153 | 27 | 0 | 0 |
| 17 | Sagarin Predictive | 0.85000 | 0.00000 | 8.4108 | -0.1642 | 113.624 | 180 | 153 | 27 | 0 | 0 |
| 18 | PerformanZ Ratings | 0.85000 | 0.00000 | 9.0991 | -0.4931 | 134.235 | 180 | 153 | 27 | 0 | 0 |
| 19 | Laz Index | 0.84444 | 0.00000 | 8.9228 | 0.0041 | 136.239 | 180 | 152 | 28 | 0 | 0 |
| 20 | Born Power Index | 0.83889 | 0.00000 | 8.1017 | 1.0661 | 108.572 | 180 | 151 | 29 | 0 | 0 |
| 21 | NationalSportsRankings | 0.81667 | 0.00000 | 8.7316 | 0.1955 | 135.696 | 180 | 147 | 33 | 0 | 0 |
| 22 | Sonny Moore | 0.81667 | 0.00000 | 8.8931 | 0.7704 | 141.427 | 180 | 147 | 33 | 0 | 0 |
| 23 | Ashby AccuRatings | 0.81111 | 0.00000 | 9.9333 | 0.7556 | 170.941 | 180 | 146 | 34 | 0 | 0 |
| 24 | Stat Fox | 0.79444 | 0.00000 | 9.5722 | 0.9611 | 152.756 | 180 | 143 | 37 | 0 | 0 |
| 25 | NutShell Sports | 0.77778 | 0.00000 | 12.1561 | 2.8494 | 260.380 | 180 | 140 | 40 | 0 | 0 |
| 26 | Stortrends | 0.75843 | 0.00000 | 10.6067 | -0.9663 | 191.576 | 178 | 135 | 43 | 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