ThePredictionTracker NCAA RESULTS

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

2014 Retrodiction Results

Through

Rank	System	Pct. Correct	Absolute Error	Bias	Mean Square Error	games	suw	sul
1	Logistic Regression	0.83421	15.3849	-1.7076	639.423	760	634	126
2	Sagarin Elo	0.83289	11.3897	0.7004	208.562	760	633	127
3	Least Squares w/ HFA	0.82632	9.2885	0.0512	135.151	760	628	132
4	Payne Power Ratings	0.81579	11.0928	-0.2774	195.876	760	620	140
5	Massey Concensus Rank	0.81447	11.0212	0.9871	197.717	760	619	141
6	Sagarin	0.80921	10.5521	0.5754	179.995	760	615	145
7	System Average	0.80658	10.7080	0.7210	184.020	760	613	147
8	system Median	0.80263	10.6445	0.7746	182.142	760	610	150
9	Beck Elo	0.80263	11.1433	0.3585	199.185	760	610	150
10	Least Squares	0.80000	10.4506	0.8218	173.854	760	608	152
11	CPA Retro	0.79342	11.7421	0.7469	229.051	760	603	157
12	CPA Rankings	0.79211	10.5370	0.7913	176.040	760	602	158
13	NutShell Combo	0.79079	11.5542	0.4336	223.363	760	601	159
14	Born Power Index	0.79079	10.9884	1.4090	192.659	760	601	159
15	Sagarin Predictive	0.78947	10.6223	0.5138	179.152	760	600	160
16	PerformanZ Ratings	0.78947	11.2891	0.8602	198.884	760	600	160
17	NutShell Sports	0.78947	11.9673	0.1682	231.625	760	600	160
18	Sonny Moore	0.78684	11.1638	0.9848	196.186	760	598	162
19	Edward Kambour	0.78026	10.6716	1.1649	182.119	760	593	167
20	Laz Index	0.77895	10.8580	0.6309	189.538	760	592	168
21	Covers.com	0.77895	11.8271	0.0870	224.369	760	592	168
22	Ashby AccuRatings	0.77368	10.9395	1.7062	193.157	760	588	172
23	Nutshell Girl	0.77105	11.8099	0.6992	237.484	760	586	174
24	Pigskin Index	0.76579	11.1697	0.8485	199.925	760	582	178
25	Stat Fox	0.76053	11.1237	1.9051	192.928	760	578	182
26	SuperList	0.75658	12.5472	0.7683	256.469	760	575	185
27	Stortrends	0.76612	11.5045	0.2327	208.121	667	511	156

* 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