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

2008 Retrodiction Results

System Pct. Correct Against Spread Absolute Error Bias Mean Square Error games suw sul atsw atsl
Least Squares w/ HFA0.822380.000009.42490.1467138.64971558812700
PerformanZ Ratings0.798600.0000011.2465-0.6441201.53471557114400
Sagarin Predictive0.794410.0000010.7132-0.6661183.51571556814700
Beck Elo0.794410.0000010.7993-0.6846202.06271556814700
Born Power Index0.794410.0000011.02060.3013193.19271556814700
CPA Retro0.793010.0000011.41220.8321224.22971556714800
Sonny Moore0.791610.0000010.9238-0.0045194.39871556614900
CPA Rankings0.787410.0000010.54930.9923178.43171556315200
Stat Fox0.784620.0000010.81120.8056188.26571556115400
NutShell Sports0.781820.0000011.18380.0708200.41871555915600
Pigskin Index0.779020.0000011.0741-0.2238201.77671555715800
NutShell Retro0.776220.0000011.19280.1162202.74971555516000
Wolfe *0.800000.0000011.40450.5148215.35271557214300
Laz Index0.802800.0000010.7286-0.3335194.15571557414100
Least Squares0.802800.0000010.5116-0.2513175.77371557414100
Sagarin0.818180.0000010.9679-0.7726199.40671558513000
SuperList0.816780.0000012.39630.2819242.26671558413100
Massey Concensus Rank0.813990.0000011.28100.0750210.91871558213300
Sagarin Elo0.809790.0000011.5516-0.8605227.88971557913600
Massey BCS *0.809790.0000011.7891-0.1096240.38571557913600
system Median0.808390.0000010.5103-0.1635185.65371557813700
Logistic Regression0.808390.0000014.1795-4.2595345.51171557813700
System Average0.805590.0000010.4871-0.1082183.71571557613900
Colley Rankings *0.805590.0000011.54090.1077224.21871557613900
Anderson/Hester *0.804260.0000011.5328-0.0564226.21270556713800
Martien Maas0.804200.0000011.27570.3033213.62671557514000
Ashby AccuRatings0.756640.0000011.66150.3133225.49671554117400

* 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