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

2008 Season Totals

System Pct. Correct Against Spread Absolute Error Bias Mean Square Error games suw sul atsw atsl
System Median0.754870.4805812.8794-0.2401270.866718542176334361
System Average0.754870.4808012.9140-0.2240270.949718542176338365
Atomic Football0.752090.4921512.84790.0911266.434718540178345356
CPA Rankings0.749300.5248913.3203-0.2382289.026718538180369334
Stat Fox0.747910.5388112.87050.9515273.741718537181361309
Dokter Entropy0.746520.4758513.15750.5936281.082718536182335369
Edward Kambour0.745910.4946913.34160.4994287.046673502171326333
Linear Regression0.745610.5014813.3796-0.8116288.75734225587169168
Moore Power Ratings0.743730.4914813.1593-0.4516281.757718534184346358
NutShell Sports0.743730.5085213.15220.0385283.134718534184358346
Laz Index0.742340.5028513.1206-0.6036282.273718533185353349
Massey Consensus0.740950.4914813.62420.1080300.364718532186346358
PerformanZ Ratings0.739550.4751113.9043-0.4733308.905718531187334369
Line (updated)0.7381612.59120.1024255.867718530188
Computer Adjusted Line0.738160.4789312.60720.0738256.741718530188125136
Ashby AccuRatings0.738160.4687513.13930.4153279.280718530188315357
Harmon Forcast0.737800.4917812.9010-0.1646270.614717529188329340
Bihl System0.737080.5011413.0810-0.3526274.910445328117219218
Sagarin Predictive0.736770.4971613.2170-0.4181280.841718529189350354
Lee Burdorf0.736770.4978513.2455-0.3589281.820718529189348351
Sagarin0.736770.4850613.3644-0.4172291.403718529189341362
Pigskin Index0.736250.4569213.0734-0.2268275.667709522187297353
Dunkel Index0.736030.5042712.90180.6649273.168716527189354348
Covers.com0.735380.5085713.0702-0.5363278.854718528190356344
Super List0.733980.4822215.37910.4898369.664718527191339364
ARGH Power Ratings0.732590.4785813.26950.1560288.412718526192324353
Keeper0.731200.4829513.49050.4086288.850718525193340364
Hank Trexler0.729810.4793913.0362-0.3343275.688718524194314341
Born Power Index0.729810.5071013.2065-0.1040280.310718524194357347
Line (opening)0.729050.4745812.78840.0216264.500716522194280310
Warren Claassen0.725630.4907514.0176-1.0525316.050718521197345358
Howell0.725630.4910213.3831-0.0236291.982718521197328340
Dave Congrove0.724230.5035613.2581-0.8393285.592718520198354349
Stephen Kerns0.723850.5391213.6591-2.9885305.183717519198379324
Imes Comprank0.723310.4830813.7986-0.3628304.556665481184314336
Beck Elo0.722840.4786313.4931-0.4882294.166718519199336366
Marsee0.720650.4960613.56911.3284298.360673485188315320
NutShell Retro0.717270.4793713.57500.0755299.352718515203337366
Massey BCS *0.716370.4925813.5732-0.8457313.23234224597166171
CPA Retro0.715880.4815314.1334-0.1177326.773718514204339365
DP Dwiggins0.714290.5090313.5109-3.0640296.301567405162282272
Nutshell Girl0.707600.5074213.5932-1.5051302.535342242100171166
Anderson/Hester *0.707100.4774813.8421-1.3609320.21933823999159174
Sagarin Elo0.706130.4801114.1104-0.3101326.758718507211338366
Catherwood Ratings0.704550.5170113.0714-0.5325279.34330821791152142
Martien Maas0.702210.4948714.0884-0.1875328.068497349148241246
Colley Rankings *0.701750.4791713.9185-0.9162320.895342240102161175
Wolfe *0.701750.5103914.0233-0.3427329.651342240102172165
Bassett Model0.699480.4780313.3794-0.1183290.850579405174272297
Tom Benson0.699230.4814814.6618-1.0881347.855522365157247266
Sportrends0.693500.4956414.8414-1.3575367.346708491217341347
Billingsly0.686630.4573914.4297-0.5499335.311718493225322382
Logistic Regression0.672510.4985219.9079-4.7427967.244342230112168169
Least Squares w/ HFA0.657890.4925816.1102-1.1122412.168342225117166171

* 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