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

2011 Second Half Totals

Through 2012-01-10
Rank System Pct. Correct Against Spread Absolute Error Bias Mean Square Error games suw sul atsw atsl
1Anderson/Hester *0.705260.5226712.9407-1.3138268.741380268112196179
2ARGH Power Ratings0.699210.5303912.4769-1.0508250.428379265114192170
3Ashby AccuRatings0.726320.5114312.5185-1.4494240.788380276104179171
4Atomic Football0.697370.4880012.5323-1.0546244.373380265115183192
5Bassett Model0.694740.4586713.4253-0.2361268.709380264116172203
6Beck Elo0.702630.4880012.7144-1.2588257.107380267113183192
7Betgrinders.com0.690300.5538512.6370-1.3646235.52826818583144116
8Bias Free Rankings0.707120.4933012.9153-1.5560256.136379268111184189
9Bihl System0.713530.5175212.4006-0.8664241.085377269108192179
10Billingsley0.689470.5040013.0826-1.3491269.212380262118189186
11Billingsley+0.692110.4746712.9836-1.4483259.138380263117178197
12Born Power Index0.707890.5080212.8746-1.4309258.254380269111190184
13Brent Craig0.702630.4826712.6972-0.7927256.881380267113181194
14Catherwood Ratings0.718420.4632812.9342-0.3658258.861380273107164190
15CF By the Numbers0.673680.5057512.7237-0.8553248.824380256124176172
16Colley Rankings *0.705260.5253312.9895-1.3711268.107380268112197178
17Compughter Ratings0.720340.4511513.3292-1.7696268.57535425599157191
18Computer Adjusted Line0.721050.4958712.2487-1.0382234.1643802741066061
19Covers.com0.721050.5244612.8658-1.8110260.285380274106193175
20CPA Rankings0.713160.4880012.8769-0.7553250.869380271109183192
21CPA Retro0.676320.5066713.6992-0.9582299.289380257123190185
22Dave Congrove0.710530.5066712.5505-1.4174247.731380270110190185
23Dokter Entropy0.718420.4557612.6212-0.7667243.336380273107170203
24DP Dwiggins0.724640.5029413.2079-4.7775276.04234525095171169
25Dunkel Index0.728950.5493312.5766-0.6602249.759380277103206169
26Edward Kambour0.718420.4800012.9061-1.1087254.119380273107180195
27football.loudsound.org0.704350.5015413.4145-5.0261284.157345243102163162
28Hank Trexler0.709760.4985812.4960-2.8338247.968379269110176177
29Howell0.718420.5263212.5303-1.1513248.942380273107190171
30Keeper0.697370.5080613.1155-0.3640272.964380265115189183
31Laffaye RWP0.726320.5146713.7204-4.4626307.249380276104193182
32Laffaye XWP0.702630.4905713.2048-2.9126285.210380267113182189
33Laz Index0.721050.4826712.7159-1.7421251.519380274106181194
34Least Squares w/ HFA0.673680.5200015.4754-0.2857388.178380256124195180
35Lee Burdorf0.694740.5120612.8852-1.3820259.880380264116191182
36Line (opening)0.713160.5196412.3368-1.1132238.575380271109172159
37Line (updated)0.7236812.2421-0.9763234.447380275105
38Linear Regression0.697370.4906712.9274-0.9330258.805380265115184191
39Logistic Regression0.697370.5253314.8958-4.5280371.237380265115197178
40Marsee0.715040.5271712.64910.3588248.211379271108194174
41Martien Maas0.705260.5333316.5842-0.6973431.091380268112200175
42Massey *0.700000.5306713.0379-1.0785275.920380266114199176
43Massey Consensus0.707890.5226712.8505-1.2318263.411380269111196179
44Massey Ratings0.705260.5000012.6726-1.0268249.617380268112187187
45Moore Power Ratings0.715790.5120012.5384-1.5206246.132380272108192183
46NationalSportsRankings0.721050.4986712.4550-1.3577239.479380274106187188
47NutShell Combo0.723680.4880012.9457-1.5782261.480380275105183192
48Nutshell Girl0.684210.5226713.7637-1.8425298.378380260120196179
49NutShell Sports0.715790.5254713.4466-1.6097288.099380272108196177
50Payne Power Ratings0.697370.4640012.9560-0.7932258.646380265115174201
51PerformanZ Ratings0.700000.4946513.2069-1.1904272.648380266114185189
52Pi-Rate Ratings0.717680.4959612.7018-1.2613252.290379272107184187
53Pigskin Index0.715790.5100312.5790-1.6208249.395380272108178171
54Pointshare Ratings0.709760.5189212.7821-0.5161255.091379269110192178
55Regression-Based Analys0.713160.4785113.1158-0.7421264.595380271109167182
56Sagarin0.707890.5360012.6382-1.6012255.308380269111201174
57Sagarin Elo0.702630.5174313.2962-1.5678284.955380267113193180
58Sagarin Predictive0.718420.4826712.6748-1.5903250.979380273107181194
59Schmidt Comp. Ratings0.715790.5213912.7382-1.5583257.109380272108195179
60Sportrends0.679140.4816914.2513-1.1390311.714374254120171184
61Stat Fox0.713160.4435012.8001-0.2313248.037380271109157197
62Stephen Kerns0.715790.4663113.0276-1.4044262.192380272108173198
63Super List0.715790.5146713.9920-1.1930312.525380272108193182
64System Average0.718420.5226712.3585-1.3686240.100380273107196179
65System Median0.718420.5311712.3097-1.3227238.165380273107196173
66Tempo Free Gridiron0.739470.5264613.0500-3.2868274.00338028199189170
67TW Rankings0.000000.0000025.0000-25.0000625.00010101
68Warren Claassen0.718420.5040012.8058-1.7948258.561380273107189186
69Wolfe *0.700000.5120013.2549-0.8268281.214380266114192183

* 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