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

2012 Last Week

Through 2013-01-07
Rank System Pct. Correct Against Spread Absolute Error Bias Mean Square Error games suw sul atsw atsl
1Catherwood Ratings0.628570.7333312.0571271.257352213228
2Bias Free Rankings0.714290.6363613.4340337.7163525102112
3Dunkel Index0.714290.6060613.0986321.1673525102013
4Born Power Index0.714290.6060613.2343309.6633525102013
5Line (opening)0.628570.6000013.4429299.0643522131510
6Daniel Curry Index0.742860.5937513.2571302.229352691913
7Stat Fox0.685710.5937513.1709276.6463524111913
8Keeper0.657140.5757613.8257339.8753523121914
9testing new method0.600000.5757614.1783307.0813521141914
10Laz Index0.657140.5757613.9237311.4873523121914
11Atomic Football0.628570.5757613.4283297.1233522131914
12Pigskin Index0.685710.5714313.2289292.2593524111612
13CF By the Numbers0.685710.5517213.4854303.5323524111613
14CPA Rankings0.657140.5454513.6671318.5883523121815
15SID ratings0.657140.5454514.3117343.5913523121815
16Ted Thompson SPRS0.685710.5454514.6346329.6913524111815
17Dave Congrove0.685710.5454513.5794296.0503524111815
18Directorofinformation0.628570.5454514.1580331.7913522131815
19Moore Power Ratings0.714290.5454512.9417281.7973525101815
20Compughter Ratings0.656250.5333314.4469346.4973221111614
21Linear Regression0.628570.5151514.4597357.0723522131716
22Beck Elo0.628570.5151514.1089331.2033522131716
23Billingsley+0.600000.5151514.0140303.0023521141716
24DP Dwiggins0.600000.5151515.5029381.0393521141716
25Ted Thompson Avg0.657140.5000013.6140306.9683523121515
26Tempo Free Gridiron0.714290.5000014.2000310.2003525101515
27Regression-Based Analys0.600000.5000014.4571329.2573521141515
28Pi-Ratings Vintage0.657140.4848513.9143321.2713523121617
29Edward Kambour0.600000.4848514.2703348.2613521141617
30NutShell Combo0.628570.4848514.6029333.4423522131617
31Payne Power Ratings0.657140.4848514.0660336.2833523121617
32Sagarin Predictive0.685710.4848513.9254321.6443524111617
33Covers.com0.657140.4848514.7434332.5123523121617
34Least Squares w/ HFA0.685710.4848516.3926471.8573524111617
35Brent Craig0.612900.4838715.5545402.6153119121516
36Hank Trexler0.628570.4666714.4571317.9433522131416
37Sportrends0.647060.4666714.3529338.8823422121416
38Marsee0.628570.4545514.6000345.8003522131518
39Nutshell Girl0.542860.4545514.5491330.2193519161518
40NationalSportsRankings0.742860.4545513.8551318.052352691518
41Anderson/Hester *0.457140.4545516.6580418.8303516191518
42Stephen Kerns0.628570.4545514.8769359.8803522131518
43Bihl System0.628570.4545514.3874338.4553522131518
44System Average0.657140.4545514.0300321.6163523121518
45Dokter Entropy0.657140.4545513.5694290.5913523121518
46System Median0.685710.4375013.8560315.5073524111418
47Schmidt Comp. Ratings0.676470.4375014.2747325.7573423111418
48Warren Claassen0.542860.4242415.8329380.7603519161419
49Pointshare Ratings0.685710.4242414.1657320.6303524111419
50Pi-Rate Ratings0.657140.4242413.5229300.5813523121419
51Logistic Regression0.485710.4242420.1494629.9813517181419
52PerformanZ Ratings0.714290.4242413.6214315.2423525101419
53Massey Ratings0.685710.4230814.4000338.4003524111115
54Howell0.542860.4062515.6143383.1793519161319
55Massey Consensus0.600000.4062515.3097364.4143521141319
56Ashby AccuRatings0.657140.4000014.0857311.9713523121218
57Colley Rankings *0.457140.3939416.7437420.4173516191320
58Sagarin Elo0.457140.3939416.5960405.2783516191320
59Laffaye XWP0.571430.3939418.9743567.5253520151320
60Super List0.571430.3939416.5166417.4633520151320
61Laffaye RWP0.628570.3939415.7346377.2383522131320
62Sagarin0.628570.3939415.2637355.9183522131320
63NutShell Sports0.628570.3939414.9371362.4923522131320
64Fremeau FEI0.600000.3871016.1143381.7143521141219
65ARGH Power Ratings0.657140.3666715.3929377.1773523121119
66Wolfe *0.514290.3636416.9711424.1773518171221
67Massey *0.485710.3636416.9766417.6693517181221
68CPA Retro0.542860.3333316.6857414.7903519161122
69Billingsley0.485710.3333316.0246365.1093517181122
70Computer Adjusted Line0.657140.2857113.5286299.45035231225
71Line (updated)0.6571413.4714298.950352312
* 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