Computer Ratings
|
2011-12 National Hockey League
Computer Ratings |
|
This is my first rough attempt at a computer rating that can, among other things, come somewhat close to predicting final game scores. The actual computer rating, which describes team performance based on games played to date, is found under the "Rating" column. To determine a hypothetical margin of victory, use the "Pts" column. You can the calculation for some upcoming games on the right. Don't forget to add in home "field" advantage, which is listed just below the current predictions on the right.
Ratings last updated Sunday 02/19/12, 10:05 AM ET
-----------------------------------------------------------------
BCS-Style
Rank Team W L Rating Pts Rank
-----------------------------------------------------------------
1 Detroit 40 19 3.803 0.78 1
2 NY Rangers 37 19 3.323 0.67 2
3 Boston 35 21 3.260 0.94 5
4 Vancouver 37 21 2.762 0.61 4
5 St Louis 36 22 2.576 0.50 3
6 Pittsburgh 33 25 2.256 0.55 7
7 San Jose 31 25 2.140 0.60 9
8 Nashville 33 25 1.716 0.27 6
9 Philadelphia 32 26 1.348 0.33 10
10 New Jersey 33 24 0.779 -0.03 8
11 Phoenix 29 30 0.357 0.16 12
12 Dallas 29 29 0.164 0.01 11
13 Chicago 31 28 0.081 0.04 13
14 Calgary 28 31 -0.260 -0.08 14
15 Toronto 29 30 -0.294 -0.05 17
16 Ottawa 30 30 -0.362 -0.12 15
17 Washington 29 29 -0.591 -0.14 18
18 Colorado 29 30 -0.626 -0.22 16
19 Los Angeles 27 32 -0.671 -0.02 21
20 Winnipeg 29 31 -1.070 -0.35 19
21 Anaheim 24 34 -1.446 -0.32 22
22 Edmonton 22 35 -1.502 -0.22 25
23 Montreal 24 35 -1.570 -0.17 28
24 Tampa Bay 26 32 -1.753 -0.51 20
25 Minnesota 25 33 -1.835 -0.40 24
26 Florida 26 31 -1.972 -0.52 23
27 NY Islanders 24 34 -2.179 -0.52 26
28 Buffalo 24 34 -2.323 -0.53 27
29 Carolina 23 36 -2.426 -0.47 29
30 Columbus 17 41 -3.683 -0.80 30
(The "BCS style" ranking is one based entirely on wins and losses, similar to what
is used in college football.)
|
PREDICTIONS FOR UPCOMING GAMES
Date Away Team Home Team Prediction
---------- ------------------------ ------------------------ --------------
Sun 19 Feb Pittsburgh Buffalo AWAY by -0.77
Sun 19 Feb San Jose Detroit HOME by 0.48
Sun 19 Feb Boston Minnesota AWAY by -1.04
Sun 19 Feb St Louis Chicago AWAY by -0.16
Sun 19 Feb New Jersey Montreal HOME by 0.16
Sun 19 Feb Anaheim Florida HOME by 0.11
Sun 19 Feb Columbus NY Rangers HOME by 1.77
Sun 19 Feb Nashville Dallas HOME by 0.04
Sun 19 Feb Vancouver Edmonton AWAY by -0.52
Sun 19 Feb Colorado Winnipeg HOME by 0.18
Mon 20 Feb Ottawa NY Islanders AWAY by -0.09
Mon 20 Feb Washington Carolina AWAY by -0.02
Tue 21 Feb NY Islanders Buffalo HOME by 0.29
Tue 21 Feb New Jersey Toronto HOME by 0.28
Tue 21 Feb NY Rangers Pittsburgh HOME by 0.18
Tue 21 Feb San Jose Columbus AWAY by -1.10
Tue 21 Feb Dallas Montreal HOME by 0.13
Tue 21 Feb Anaheim Tampa Bay HOME by 0.12
Tue 21 Feb Vancouver Nashville AWAY by -0.04
Tue 21 Feb Detroit Chicago AWAY by -0.44
Tue 21 Feb Philadelphia Winnipeg AWAY by -0.37
Tue 21 Feb Edmonton Calgary HOME by 0.44
Tue 21 Feb Los Angeles Phoenix HOME by 0.49
Wed 22 Feb Washington Ottawa HOME by 0.33
Wed 22 Feb Boston St Louis AWAY by -0.13
Wed 22 Feb Los Angeles Colorado HOME by 0.11
Thu 23 Feb San Jose Toronto AWAY by -0.35
Thu 23 Feb Anaheim Carolina HOME by 0.15
Thu 23 Feb Minnesota Florida HOME by 0.19
Thu 23 Feb Vancouver Detroit HOME by 0.48
Thu 23 Feb St Louis Nashville HOME by 0.07
Thu 23 Feb Tampa Bay Winnipeg HOME by 0.47
Thu 23 Feb Dallas Chicago HOME by 0.34
Thu 23 Feb Phoenix Calgary HOME by 0.06
Thu 23 Feb Philadelphia Edmonton AWAY by -0.24
Current home field advantage is: 0.30 MAE for games to date: 1.86 These ratings fit to produce 0.59 of the correct winners. Pct when predicted MOV is above 0.61: 0.68 A favored away team rarely loses when favored by more than -0.53. A favored home team rarely loses when favored by more than 0.66. Above are some statistics about the ratings model. Home "field" advantage is shown first. MAE is the mean absolute error of the ratings fit to all the games played to date. This number is usually larger than you think it should be, but to me it's a good measure of how variable (or maybe "predictable") game outcomes can be. Immediately below that, you can see how this best fit does in retro-predicting (there's a better word I'm sure) just the game winners. My favorite stats are the last two--when the home or away team is favored by the given margin, they only lose 30 percent of the time. This is the kind of information that people in the sports wagering world might find useful. |
About the author
I have a Ph.D. in Atmospheric Science from the University of Alabama in Huntsville. I now work in Boulder, Colorado, in the broad areas of science education and numerical weather prediction (that is, forecasting the weather using computer models). Contact me using this email form if you have questions or non-hateful comments.