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