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

2012 Season Totals

Through 2013-01-07
Rank System Pct. Correct Against Spread Absolute Error Bias Mean Square Error games suw sul atsw atsl
1Hank Trexler0.768180.5391412.5350-1.9885254.549729560169365312
2Sagarin Predictive0.765030.5299912.4721-0.5048251.843732560172380337
3Laz Index0.765030.5529212.5917-0.9660256.549732560172397321
4Line (updated)0.7633412.2079-0.0999237.353731558173
5System Median0.762300.5345812.2820-0.4177243.088732558174371323
6System Average0.762300.5292512.2988-0.3715243.839732558174380338
7Sagarin0.762300.5445712.5498-0.5195254.382732558174391327
8SID ratings0.762300.5244112.6688-1.5823261.434732558174376341
9Computer Adjusted Line0.761970.5625012.1881-0.1307237.003731557174144112
10Born Power Index0.760930.5062812.8769-0.1989269.676732557175363354
11Daniel Curry Index0.759800.5274312.7530-0.0036264.855587446141298267
12Massey Ratings0.759560.5443612.4536-0.5280253.068732556176362303
13Billingsley+0.759560.4979112.8117-0.2970262.695732556176357360
14Catherwood Ratings0.758200.5182512.85380.4433265.720732555177355330
15Schmidt Comp. Ratings0.756870.5196112.7966-0.5800264.131728551177371343
16Pigskin Index0.756830.5051412.5029-0.5291248.995732554178344337
17Ted Thompson Avg0.754100.5159812.2891-0.2964242.629732552180339318
18NationalSportsRankings0.754100.4734612.6557-0.3468253.394732552180339377
19Compughter Ratings0.753800.5267612.7520-0.9668262.787723545178374336
20Super List0.752730.5188314.17720.1546319.551732551181372345
21Massey Consensus0.752730.5349212.7017-0.0788261.022732551181383333
22CPA Rankings0.752410.5344312.8132-0.0172266.583622468154326284
23Keeper0.750000.5293313.00000.6739270.419732549183379337
24Dokter Entropy0.748630.4902512.45940.0421243.702732548184352366
25ARGH Power Ratings0.747270.5406612.7541-0.2443260.894732547185379322
26Moore Power Ratings0.747270.4791112.7913-0.4013262.599732547185344374
27NutShell Combo0.747270.5341712.9937-1.1380276.958732547185383334
28PerformanZ Ratings0.747270.5244113.1356-0.9055281.988732547185376341
29Fremeau FEI0.746240.5060713.8464-0.1596306.861599447152292285
30Pi-Rate Ratings0.745550.5056212.6317-0.1454253.375731545186360352
31Edward Kambour0.744830.5183112.6932-0.4261256.244725540185368342
32Payne Power Ratings0.744540.5320313.0152-0.0932278.157732545187382336
33Atomic Football0.744540.4979112.5863-0.1889248.557732545187357360
34CF By the Numbers0.744540.5297512.47540.0174252.514732545187365324
35Line (opening)0.744190.4872612.3338-0.1545244.285731544187306322
36Dunkel Index0.743170.5027913.0293-0.7408272.727732544188361357
37Ashby AccuRatings0.741800.4977812.6421-0.4200252.091732543189337340
38Stat Fox0.741800.4849412.86330.8023262.701732543189338359
39Directorofinformation0.741800.5153612.9370-0.3157270.648732543189369347
40DP Dwiggins0.740440.5237413.1974-3.8482281.477732542190375341
41Bias Free Rankings0.740440.5230113.6575-0.2906309.152732542190375342
42Martien Maas0.738760.5441617.31520.4494481.61535626393191160
43Brent Craig0.738650.5280112.6198-0.6077258.661727537190377337
44Linear Regression0.738460.5459312.4589-0.3380257.115390288102208173
45Tempo Free Gridiron0.736340.4775713.1612-1.9211278.314732539193330361
46Howell0.734970.5343112.8922-0.1957265.284732538194366319
47Pi-Ratings Vintage0.734610.5240212.8242-0.7249263.241731537194360327
48Ted Thompson SPRS0.733610.5362112.9674-0.0197266.559732537195385333
49NutShell Sports0.733610.5112713.9676-1.2123317.670732537195363347
50Fort Heresy Model0.732560.4352914.14310.4187308.5158663233748
51Laffaye RWP0.732240.5236814.1205-0.6736321.082732536196376342
52Bihl System0.731960.5616812.8291-0.5527270.438388284104214167
53Beck Elo0.729510.5278612.9636-0.4220271.971732534198379339
54Pointshare Ratings0.729270.5096313.1973-1.9799292.776591431160291280
55Dave Congrove0.726780.5097512.8353-0.6741269.486732532200366352
56Wolfe *0.726340.5208313.50930.3424290.177391284107200184
57Warren Claassen0.725410.5376013.5271-1.1966300.707732531201386332
58CPA Retro0.723470.4901613.7821-0.0321303.591622450172299311
59Anderson/Hester *0.721230.5312513.40080.0363287.225391282109204180
60Least Squares w/ HFA0.720510.5602115.4152-0.0579410.972390281109214168
61Regression-Based Analys0.719950.4800613.42080.6973290.779732527205325352
62Sagarin Elo0.718580.5146413.4536-0.5851287.024732526206369348
63Colley Rankings *0.716110.5208313.4440-0.1469288.363391280111200184
64Laffaye XWP0.715340.5242415.22054.3356365.744678485193346314
65Marsee0.714480.5320113.77871.3788307.019732523209374329
66Billingsley0.714480.5292513.4513-0.4277291.181732523209380338
67Nutshell Girl0.714480.5154113.5645-1.1495303.928732523209368346
68Stephen Kerns0.712170.5038113.8096-0.7033309.033674480194331326
69Logistic Regression0.710260.4778115.3340-3.2139376.918390277113183200
70Covers.com0.709020.5125713.5973-1.2167304.345732519213367349
71Massey *0.705880.5000013.54680.0672294.319391276115191191
72Sportrends0.702030.4819713.4267-0.6862288.451641450191294316
73football.loudsound.org0.701880.5229414.0955-4.8538330.744691485206342312
74testing new method0.686380.5209413.83002.6846314.082389267122199183

* 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