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

2021 Season Totals

Through 2022-01-11
Rank System Pct. Correct Against Spread Absolute Error Bias Mean Square Error games suw sul atsw atsl
1Massey Ratings0.690910.4828913.4370-0.0081276.138770532238367393
2Daniel Curry Index0.689610.4671113.87910.1010298.036770531239355405
3ARGH Power Ratings0.716880.5000013.4558-0.1104281.555770552218369369
4Payne Power Ratings0.703900.4671113.6009-0.1149286.661770542228355405
5Talisman Red0.689940.4908113.34320.1340271.022716494222347360
6Howell0.708330.4938913.5013-0.1457282.844768544224364373
7Billingsley0.711690.4822113.88260.1543304.154770548222366393
8Laffaye RWP0.701410.5035913.86640.2000304.175710498212351346
9Donchess Inference0.716880.4738313.28990.2138267.461770552218353392
10Bihl System0.693240.4939213.07530.2528258.480414287127203208
11Sagarin Points0.692210.4585013.35170.2749270.378770533237348411
12Line (opening)0.707790.5000012.75260.2760251.696770545225337337
13David Harville0.703900.4591013.14670.2825262.413770542228348410
14Sagarin Ratings0.690910.4473713.25410.2903266.691770532238340420
15DP Dwiggins0.691910.4958913.92950.3133304.002766530236362368
16FEI Projections0.682770.5041213.03170.3315257.875621424197306301
17Payne Predict0.690910.4631613.86720.3339301.146770532238352408
18Sagarin Golden Mean0.681820.4671113.51860.3441283.960770525245355405
19Line (updated)0.718180.5000012.62470.4247245.711770553217165165
20Sagarin Recent0.692210.4789513.56770.4317292.251770533237364396
21Computer Adjusted Line0.712990.4767412.65910.4734246.306770549221205225
22Line (Midweek)0.7116912.64290.4740246.300770548222
23Linear Regression0.690770.4974713.19280.4825267.460401277124197199
24Dokter Entropy0.716510.4597113.14050.5041262.208769551218348409
25PerformanZ Ratings0.709090.4795814.02440.5273308.273770546224364395
26Brent Craig0.708430.5194213.07990.5354263.541415294121214198
27System Average0.706490.4861712.96460.5539255.949770544226369390
28System Median0.701300.4741012.95980.5655255.160770540230357396
29Least Squares w/ HFA0.665840.5151515.65820.6268372.986401267134204192
30Moore Power Ratings0.692210.4881613.42320.6346279.246770533237371389
31Catherwood Ratings0.770270.5000013.74320.6351276.443148114347070
32Laz Index0.714290.4868113.16090.6398263.527770550220369389
33Versus Sports Simulator0.701430.4676413.32600.6634271.270767538229354403
34Edward Kambour0.709090.4815813.28060.6883265.528770546224366394
35Payne W/L0.712990.4762514.3145-0.7173318.431770549221361397
36Roundtable0.692310.5019813.62660.7186293.881533369164253251
37TeamRankings.com0.703900.4827113.11300.7473263.278770542228363389
38Beck Elo0.696100.4947413.45830.7619284.370770536234376384
39Cleanup Hitter0.668830.4731214.32280.8333319.305770515255352392
40Pigskin Index0.683120.5021113.19470.9822262.218770526244357354
41Dave Congrove0.682700.5052813.72530.9936288.525769525244383375
42Pi-Ratings Mean0.709090.4939813.13661.0153261.875770546224369378
43Stephen Kerns0.688310.5072513.90701.0216301.969770530240385374
44Pi-Rate Ratings0.698700.5053113.20491.0277264.988770538232381373
45PI-Rate Bias0.710390.4953813.20861.1340264.793770547223375382
46ESPN FPI0.698700.4677213.02181.1573260.627770538232355404
47Keeper0.710350.5153113.42451.2305283.635763542221387364
48Massey Consensus0.728570.4874813.59831.2433283.608770561209370389
49Born Power Index0.684420.4855313.54101.2933278.308770527243369391
50Dunkel Index0.676300.4978013.50551.3240279.919692468224340343
51Super List0.712990.4993415.29311.5619355.876770549221378379
52Logistic Regression0.678300.4722215.4058-2.1711369.469401272129187209
53Stat Fox0.687010.4903813.41172.1963274.644770529241357371
54Loudsound.org0.653950.4796214.7039-2.9618340.061760497263353383
* 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