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

2014 Season Totals

Through 2015-01-13
Rank System Pct. Correct Against Spread Absolute Error Bias Mean Square Error games suw sul atsw atsl
1Line (updated)0.736840.5233512.47701.3191249.765760560200269245
2Computer Adjusted Line0.735530.5132312.50661.2500250.262760559201291276
3Thompson CAL0.739470.5081112.57491.1438251.332760562198376364
4Line (opening)0.720320.5225812.55470.9453251.703758546212324296
5Line (Midweek)0.7326212.49731.2580252.051748548200
6Thompson ATS0.736840.5067612.62680.9076253.703760560200375365
7Thompson Average0.731580.5027212.70091.0303256.739760556204370366
8Dokter Entropy0.730260.4966212.77481.2805257.344760555205367372
9Pi-Ratings Mean0.717110.5382512.81050.6926260.100760545215394338
10Ashby AccuRatings0.728950.5072012.77900.7397260.553760554206352342
11System Median0.730260.5151512.82450.8342261.095760555205374352
12System Average0.722370.5081312.85530.8323262.563760549211375363
13Atomic Football0.722370.5099712.89971.1315265.172760549211358344
14PI-Rate Bias0.718420.5313412.93250.9499266.871760546214390344
15Pigskin Index0.732890.5100312.96580.5319268.003760557203356342
16Pi-Rate Ratings0.722370.5359612.95601.0500269.513760549211395342
17Sagarin Ratings0.734210.4966213.07981.2648270.887760558202367372
18DirectorOfInformation0.726320.4973013.02800.5673271.395760552208368372
19Sagarin Points0.728950.4857913.01631.3367271.817760554206359380
20CPA Rankings0.734210.5027013.22780.4700273.204760558202372368
21ThePowerRank.com0.704850.5034713.10380.4475274.416742523219363358
22Laz Index0.709210.5108113.23910.2984276.767760539221378362
23Massey Consensus0.726320.5189213.21871.0745277.300760552208384356
24Billingsley+0.731580.5216213.17330.3666279.161760556204386354
25ComPughter Ratings0.708440.5027113.33540.4806280.579758537221371367
26Brent Craig 20.730880.4781313.29414.5184281.04835325895164179
27Sagarin Golden Mean0.726320.5027013.39051.2257281.650760552208372368
28Bihl System0.690830.4945113.49131.1259282.167469324145225230
29Edward Kambour0.722300.5006913.32391.1352282.256749541208365364
30Massey Ratings0.703880.5079913.2848-0.0307282.541618435183286277
31Payne Power Ratings0.728590.5162613.35950.3545282.559759553206381357
32Brent Craig0.703170.4816813.51861.3501284.228758533225355382
33ARGH Power Ratings0.721050.5028213.49511.0266285.106760548212357353
34Stat Fox0.728950.4943513.37111.8056285.530760554206350358
35Donchess Inference0.697890.5047513.46600.2313286.376758529229372365
36Linear Regression0.688350.5112413.5403-0.4773287.299369254115182174
37Sagarin Points Elo0.725000.5061113.51981.0935289.009760551209373364
38NutShell Combo0.708620.5098413.44950.4232290.404580411169285274
39Keeper0.711080.4850913.74012.0397291.578758539219358380
40Randal Horobik0.734350.4780213.73601.1337291.875591434157261285
41Beck Elo0.701280.4905113.73050.8736291.916703493210336349
42Lee Burdorf0.712400.4938813.65390.8791292.789758540218363372
43Stephen Kerns0.705160.4872513.7344-0.0158293.368736519217344362
44DP Dwiggins0.749350.4517913.67621.4726293.43038328796164199
45Nutshell Eye0.687930.5054313.54810.5517294.092580399181279273
46Howell0.705800.5106713.64050.6208294.962758535223359344
47Catherwood Ratings0.720320.5014013.67811.5831296.065758546212357355
48Moore Power Ratings0.717310.4904913.68381.1843297.639757543214361375
49Billingsley0.718420.5189213.58350.0035299.722760546214384356
50FEI Projections0.687750.5098313.77470.1225302.117759522237363349
51Born Power Index0.711840.4973013.89170.9360302.254760541219368372
52PerformanZ Ratings0.698680.5027013.86220.7613302.269760531229372368
53PointShare0.655170.5089613.8665-0.0945302.334580380200284274
54Dunkel Index0.726550.5047513.58281.4209303.465757550207372365
55Loudsound.org0.690770.5639713.5236-3.1740303.556401277124216167
56Covers.com0.698680.5286913.7098-0.2118303.723760531229387345
57Nutshell Girl0.711910.4800613.78950.8216306.373722514208337365
58Dave Congrove0.732890.4891913.75050.3377306.783760557203362378
59Marsee0.698680.4777813.99212.6526307.843760531229344376
60MDS Model0.708210.5045213.89810.0988309.047682483199335329
61Regression Based Analys0.724460.4784113.89162.3003309.165646468178288314
62Tempo Free Gridiron0.713620.5258913.6579-1.2368309.315646461185325293
63Laffaye RWP0.700000.5405413.8757-1.5578311.392760532228400340
64CPA Retro0.686840.4891914.21340.2496312.580760522238362378
65NutShell Sports0.708440.5103414.00850.0378316.792758537221370355
66Daniel Curry Index0.714100.4993214.31450.8363323.839759542217368369
67Sportrends0.685160.5134714.33730.0255332.841667457210324307
68Super List0.690790.5331514.55720.9633335.618760525235394345
69Cleanup Hitter0.706720.5059014.17612.3361336.343699494205343335
70Least Squares w/ HFA0.666670.5322115.45410.0537375.347369246123190167
71Logistic Regression0.685640.5546215.7456-2.8696389.856369253116198159
72Laffaye XWP0.692110.4782616.52096.7767425.075760526234352384
* 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