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

2009 Season Totals

Through
Rank System Pct. Correct Against Spread Absolute Error Bias Mean Square Error games suw sul atsw atsl
1Covers.com0.732490.5348812.09120.0708236.518714523191368320
2Billingsley0.732490.5287412.5430-0.0059253.321714523191368328
3Nutshell Girl0.736690.5258612.2668-0.1733244.838714526188366330
4Stephen Kerns0.725490.5258612.52910.7475256.894714518196366330
5NutShell Combo0.736690.5245011.70030.1868221.595714526188364330
6Edward Kambour0.746500.5245011.64920.7182219.689714533181364330
7Dokter Entropy0.750700.5165511.44440.7752212.719714536178359336
8Moore Power Ratings0.749300.5172911.71120.5256225.807714535179359335
9NutShell Sports0.728290.5143712.21800.5398241.651714520194358338
10Dave Congrove0.726890.5100612.0814-0.1209235.237714519195355341
11Billingsley+0.749300.5093511.75860.4208228.385714535179354341
12Sagarin Elo0.707280.5071812.74870.2918263.889714505209353343
13Beck Elo0.726890.5079412.08900.2810239.203714519195352341
14Massey Consensus0.725490.5057512.05170.6875237.293714518196352344
15Super List0.725490.5050413.58150.9087292.143714518196351344
16Warren Claassen0.708680.5043112.9084-0.4963270.781714506208351345
17Sagarin Predictive0.738100.5043111.75290.6497224.315714527187351345
18System Average0.752100.5014411.57230.4370217.049714537177349347
19Sagarin0.726890.5000011.95330.4593234.340714519195348348
20Laz Index0.749300.5014411.66670.1511221.865714535179348346
21Frank Alder0.725490.4985612.6280-0.4457260.100714518196347349
22Lee Burdorf0.732490.5036312.05810.4940238.303714523191347342
23Schmidt Comp. Ratings0.731090.4971312.05360.1328238.557714522192346350
24Atomic Football0.752100.4971311.51200.8409216.111714537177346350
25Keeper0.736690.4964012.07171.5916234.506714526188345350
26Dunkel Index0.739130.4971211.84541.1091227.489713527186345349
27ARGH Power Ratings0.742300.5104512.20170.6674239.155714530184342328
28Howell0.733520.5174012.00220.0065232.849713523190342319
29DP Dwiggins0.711960.5159312.4536-3.3892250.857677482195340319
30Born Power Index0.736690.4899112.08340.4529240.313714526188340354
31Bassett Model0.729960.4891812.46071.8703248.630711519192339354
32Tom Benson0.675560.4870314.95173.2272341.119712481231338356
33System Median0.747900.4919711.54950.4387216.008714534180337348
34PerformanZ Ratings0.724090.4827612.6587-0.0329264.096714517197336360
35Pigskin Index0.756300.4947511.54050.6110216.060714540174330337
36Stat Fox0.739500.5038211.66251.6683221.267714528186330325
37CPA Rankings0.732040.5053912.26320.1163244.168668489179328321
38CPA Retro0.724550.5046213.3387-0.0054286.861668484184328322
39Catherwood Ratings0.722690.5000011.92721.2661236.606714516198326326
40Sportrends0.705550.4931912.7319-0.1486259.673703496207326335
41Hank Trexler0.750350.4923811.8850-0.0084231.237713535178323333
42Ashby AccuRatings0.736690.4916311.75630.1601224.631714526188323334
43Marsee0.737730.4762612.68581.9677262.714713526187321353
44TW Rankings0.701520.5023613.0547-0.1404283.666660463197319316
45Harmon Forcast0.723210.4896712.2321-1.4048247.691672486186308321
46NationalSportsRankings0.748480.4846011.75920.3506225.182656491165299318
47Line (opening)0.732490.4974211.41740.8249212.248714523191289292
48Payne Power Ratings0.729170.4928612.4982-0.1746255.153576420156276284
49Martien Maas0.688210.4921613.07660.4696276.537526362164251259
50Imes Comprank0.723450.4847312.4674-0.0253250.253499361138238253
51Bihl System0.727060.4878611.84860.8618227.504425309116201211
52Logistic Regression0.717740.5359115.0370-2.4933369.468372267105194168
53Linear Regression0.733870.5276211.89220.9067228.93037227399191171
54Least Squares w/ HFA0.725810.5221013.78620.7620311.808372270102189173
55Massey *0.776880.5110511.80201.2431223.55037228983185177
56Colley Rankings *0.698920.5027612.92310.8179270.791372260112182180
57Wolfe *0.706990.4944813.46981.5001288.803372263109179183
58Anderson/Hester *0.731180.4930712.51990.7481249.200372272100178183
59Computer Adjusted Line0.738100.5166111.26121.0917206.163714527187140131
60CF By the Numbers0.699680.4390211.9457-0.5272228.92931321994126161
61Line (updated)0.7338911.26541.1814206.152714524190

* 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