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

2010 Last Week

Through
Rank System Pct. Correct Against Spread Absolute Error Bias Mean Square Error games suw sul atsw atsl
1NationalSportsRankings0.714290.6764711.9823-2.6286231.3833525102311
2System Median0.657140.6764713.1840-3.0143262.7233523122311
3NutShell Combo0.600000.6764713.1703-3.1063250.2203521142311
4Bassett Model0.619050.6500013.8262-2.1414307.92321138137
5Linear Regression0.657140.6470612.9671-2.9174258.1183523122212
6Bihl System0.657140.6470613.3703-3.2286266.4813523122212
7System Average0.600000.6176513.3197-2.8540267.0913521142113
8Brent Craig 20.685710.6176512.6000-2.2000244.1433524112113
9CPA Rankings0.628570.6176513.1009-2.4734258.6243522132113
10Born Power Index0.628570.6176511.8826-2.3911228.5433522132113
11NutShell Sports0.571430.6176512.0786-1.3831217.6403520152113
12Marsee0.628570.6060613.2857-3.1143269.6293522132013
13BG Sports0.628570.6060613.12863.7571277.8643522132013
14Howell0.657140.5882413.6143-2.2714291.4503523122014
15Sagarin0.600000.5882413.8169-3.1580286.3903521142014
16Austin Sports0.628570.5882413.2674-2.9817261.5293522132014
17Stat Fox0.685710.5882412.1711-2.5700230.1393524112014
18Edward Kambour0.657140.5882413.3020-3.2289275.8093523122014
19Catherwood Ratings0.685710.5882413.0857-2.5143265.4863524112014
20Sagarin Predictive0.657140.5882413.1383-3.2137263.6363523122014
21Lee Burdorf0.742860.5882411.8689-2.7369221.304352692014
22Payne Power Ratings0.628570.5757613.8534-3.2637293.5643522131914
23ARGH Power Ratings0.685710.5757613.4000-2.7143284.0753524111914
24Keeper0.685710.5588212.93541.3554270.6973524111915
25Laz Index0.628570.5588213.4929-3.5963280.2093522131915
26Massey Consensus0.600000.5588213.9729-3.2980300.3043521141915
27Massey Ratings0.542860.5588213.5434-2.8331270.0463519161915
28Dunkel Index0.685710.5588215.0151-1.1317397.2903524111915
29CF By the Numbers0.571430.5454513.3429-1.5143271.0573520151815
30Laffaye XWP0.714290.5454513.6769-4.2711293.9033525101815
31Covers.com0.657140.5454514.0100-4.6911313.7053523121815
32Sagarin Elo0.571430.5294114.9189-2.9029328.7973520151816
33Massey *0.571430.5294114.9674-2.5463328.6603520151816
34Super List0.514290.5294114.2900-1.1643298.1193518171816
35Pigskin Index0.685710.5294112.8000-3.7126265.0263524111816
36Warren Claassen0.657140.5294114.0697-3.2783307.4833523121816
37PerformanZ Ratings0.600000.5294113.3783-2.9697280.5943521141816
38Wolfe *0.542860.5294114.6777-2.8269323.8793519161816
39Dave Congrove0.600000.5294113.7889-2.6626279.8873521141816
40Dokter Entropy0.628570.5151514.0666-3.2837291.0953522131716
41Tempo Free Gridiron0.628570.5151513.9714-4.8286298.5433522131716
42Brent Craig0.571430.5151513.5714-3.8857311.2143520151716
43Anderson/Hester *0.571430.5000014.6220-3.6763331.8783520151717
44Least Squares w/ HFA0.657140.5000014.2331-0.0274301.5353523121717
45Martien Maas0.571430.5000016.4829-0.0771394.2553520151717
46Sportrends0.600000.5000014.0000-3.6571293.3573521141515
47Hank Trexler0.600000.4848513.8857-4.2286301.4293521141617
48Moore Power Ratings0.685710.4705912.8737-3.0869255.4413524111618
49Stephen Kerns0.628570.4705913.3200-2.4457275.5753522131618
50Billingsley0.628570.4705914.2286-3.6857304.7323522131618
51Regression-Based Analys0.600000.4687514.2571-1.7429309.1713521141517
52Computer Adjusted Line0.628570.4545513.5286-2.3286286.92135221356
53Billingsley+0.514290.4411813.5906-3.1797266.3083518171519
54Logistic Regression0.542860.4411815.2091-6.3983337.5493519161519
55Schmidt Comp. Ratings0.571430.4411814.1000-3.9263292.5603520151519
56Nutshell Girl0.514290.4411814.6617-4.8326314.9333518171519
57Ashby AccuRatings0.571430.4375014.1143-3.3143293.4863520151418
58CPA Retro0.542860.4117615.1217-4.1486354.4193519161420
59Atomic Football0.628570.4117614.2446-3.0023302.7323522131420
60Beck Elo0.571430.4117613.7823-4.3989281.3703520151420
61Line (opening)0.542860.4000014.0571-2.2000296.8863519161218
62Line (updated)0.6000013.4571-2.2000287.471352114

* 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