Computer Rating System Prediction Results for College Football (NCAA IA)

2008 Season Totals

Through
Rank System Pct. Correct Against Spread Absolute Error Bias Mean Square Error games suw sul atsw atsl
1Line (updated)0.7381612.59120.1024255.867718530188
2Computer Adjusted Line0.738160.4789312.60720.0738256.741718530188125136
3Line (opening)0.729050.4745812.78840.0216264.500716522194280310
4Atomic Football0.752090.4921512.84790.0911266.434718540178345356
5Harmon Forcast0.737800.4917812.9010-0.1646270.614717529188329340
6System Median0.754870.4805812.8794-0.2401270.866718542176334361
7System Average0.754870.4808012.9140-0.2240270.949718542176338365
8Dunkel Index0.736030.5042712.90180.6649273.168716527189354348
9Stat Fox0.747910.5388112.87050.9515273.741718537181361309
10Bihl System0.737080.5011413.0810-0.3526274.910445328117219218
11Pigskin Index0.736250.4569213.0734-0.2268275.667709522187297353
12Hank Trexler0.729810.4793913.0362-0.3343275.688718524194314341
13Covers.com0.735380.5085713.0702-0.5363278.854718528190356344
14Ashby AccuRatings0.738160.4687513.13930.4153279.280718530188315357
15Catherwood Ratings0.704550.5170113.0714-0.5325279.34330821791152142
16Born Power Index0.729810.5071013.2065-0.1040280.310718524194357347
17Sagarin Predictive0.736770.4971613.2170-0.4181280.841718529189350354
18Dokter Entropy0.746520.4758513.15750.5936281.082718536182335369
19Moore Power Ratings0.743730.4914813.1593-0.4516281.757718534184346358
20Lee Burdorf0.736770.4978513.2455-0.3589281.820718529189348351
21Laz Index0.742340.5028513.1206-0.6036282.273718533185353349
22NutShell Sports0.743730.5085213.15220.0385283.134718534184358346
23Dave Congrove0.724230.5035613.2581-0.8393285.592718520198354349
24Edward Kambour0.745910.4946913.34160.4994287.046673502171326333
25ARGH Power Ratings0.732590.4785813.26950.1560288.412718526192324353
26Linear Regression0.745610.5014813.3796-0.8116288.75734225587169168
27Keeper0.731200.4829513.49050.4086288.850718525193340364
28CPA Rankings0.749300.5248913.3203-0.2382289.026718538180369334
29Bassett Model0.699480.4780313.3794-0.1183290.850579405174272297
30Sagarin0.736770.4850613.3644-0.4172291.403718529189341362
31Howell0.725630.4910213.3831-0.0236291.982718521197328340
32Beck Elo0.722840.4786313.4931-0.4882294.166718519199336366
33DP Dwiggins0.714290.5090313.5109-3.0640296.301567405162282272
34Marsee0.720650.4960613.56911.3284298.360673485188315320
35NutShell Retro0.717270.4793713.57500.0755299.352718515203337366
36Massey Consensus0.740950.4914813.62420.1080300.364718532186346358
37Nutshell Girl0.707600.5074213.5932-1.5051302.535342242100171166
38Imes Comprank0.723310.4830813.7986-0.3628304.556665481184314336
39Stephen Kerns0.723850.5391213.6591-2.9885305.183717519198379324
40PerformanZ Ratings0.739550.4751113.9043-0.4733308.905718531187334369
41Massey BCS *0.716370.4925813.5732-0.8457313.23234224597166171
42Warren Claassen0.725630.4907514.0176-1.0525316.050718521197345358
43Anderson/Hester *0.707100.4774813.8421-1.3609320.21933823999159174
44Colley Rankings *0.701750.4791713.9185-0.9162320.895342240102161175
45Sagarin Elo0.706130.4801114.1104-0.3101326.758718507211338366
46CPA Retro0.715880.4815314.1334-0.1177326.773718514204339365
47Martien Maas0.702210.4948714.0884-0.1875328.068497349148241246
48Wolfe *0.701750.5103914.0233-0.3427329.651342240102172165
49Billingsly0.686630.4573914.4297-0.5499335.311718493225322382
50Tom Benson0.699230.4814814.6618-1.0881347.855522365157247266
51Sportrends0.693500.4956414.8414-1.3575367.346708491217341347
52Super List0.733980.4822215.37910.4898369.664718527191339364
53Least Squares w/ HFA0.657890.4925816.1102-1.1122412.168342225117166171
54Logistic Regression0.672510.4985219.9079-4.7427967.244342230112168169

* 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