Rankings

KRACH: Division I Men

Click on a column header to sort by that column.
Rank Team Rating RRWP Win % Rk W-L-T Win % Win Ratio SOS Rk SOS
1 Minnesota State 542.0 .8309 1 22-5-1 0.8036 4.091 15 141.4
2 North Dakota 501.3 .8201 3 22-6-1 0.7759 3.462 10 152.6
3 Massachusetts 462.2 .8082 5 20-5-4 0.7586 3.143 9 154.1
4 Boston College 381.1 .7780 6 17-6-1 0.7292 2.692 11 148.2
5 St. Cloud 313.3 .7442 13 20-11-0 0.6452 1.818 5 175.8
6 Minnesota 297.3 .7346 4 24-7-0 0.7742 3.429 32 91.00
7 Bemidji State 295.4 .7334 16 16-10-3 0.6034 1.522 1 196.9
8 Lake Superior 270.9 .7171 8 17-7-3 0.6852 2.176 21 128.3
9 Boston University 261.5 .7103 10 10-5-1 0.6562 1.909 13 142.6
10 AIC 251.5 .7027 2 15-4-0 0.7895 3.750 44 73.03
11 Minnesota Duluth 219.9 .6757 20 15-11-2 0.5714 1.333 6 166.6
12 Omaha 204.5 .6606 21 14-11-1 0.5577 1.261 7 163.6
13 Bowling Green 192.3 .6476 14 18-10-1 0.6379 1.762 28 111.3
14 Quinnipiac 190.7 .6458 11 17-8-4 0.6552 1.900 30 102.7
15 Michigan Tech 181.4 .6351 19 17-12-1 0.5833 1.400 18 131.0
16 Wisconsin 171.6 .6230 9 20-10-1 0.6613 1.952 34 89.89
17 Providence 158.2 .6050 22 11-9-5 0.5400 1.174 16 135.6
18 UMass Lowell 147.4 .5891 23 10-9-1 0.5250 1.105 17 134.0
19 Denver 144.1 .5841 31 10-13-1 0.4375 0.778 3 183.4
20 Clarkson 139.2 .5761 18 11-7-4 0.5909 1.444 31 97.94
21 Connecticut 133.7 .5670 27 10-11-2 0.4783 0.917 12 145.3
22 Western Michigan 133.4 .5665 28 10-12-3 0.4600 0.852 8 155.6
23 Michigan 131.8 .5637 17 15-10-1 0.5962 1.476 33 90.61
24 Canisius 127.3 .5557 12 11-6-0 0.6471 1.833 45 71.93
25 Northeastern 124.5 .5506 25 9-9-3 0.5000 1.000 24 124.5
26 Army 119.6 .5414 7 15-6-1 0.7045 2.385 50 52.32
27 Robert Morris 97.70 .4946 15 15-9-0 0.6250 1.667 47 59.88
28 St. Lawrence 92.67 .4824 30 6-8-3 0.4412 0.789 26 115.8
29 Notre Dame 89.59 .4745 24 14-13-2 0.5172 1.071 40 83.81
30 Northern Michigan 86.59 .4667 33 11-17-1 0.3966 0.657 19 129.9
31 Colgate 81.83 .4537 35 6-11-5 0.3864 0.630 22 127.3
32 RIT 80.77 .4507 25 9-9-2 0.5000 1.000 42 80.77
33 Merrimack 73.88 .4303 37 5-11-2 0.3333 0.500 14 142.1
34 Penn State 73.13 .4280 29 10-12-0 0.4545 0.833 37 87.06
35 New Hampshire 60.71 .3865 39 6-14-3 0.3261 0.484 25 121.4
36 Miami 59.04 .3804 46 5-18-2 0.2400 0.316 4 177.1
37 Mercyhurst 56.41 .3704 32 8-12-1 0.4048 0.680 41 81.47
38 Colorado College 54.68 .3638 48 4-17-2 0.2174 0.278 2 183.9
39 Niagara 51.54 .3512 35 7-12-3 0.3864 0.630 43 80.18
40 Arizona State 43.53 .3164 38 7-16-3 0.3269 0.486 38 87.06
41 Maine 40.30 .3011 43 3-11-2 0.2500 0.333 27 112.0
42 Michigan State 38.02 .2898 41 7-18-2 0.2963 0.421 36 87.22
43 Sacred Heart 37.31 .2863 34 6-10-2 0.3889 0.636 48 57.22
44 Ohio State 35.82 .2786 42 7-19-1 0.2778 0.385 35 89.56
45 LIU 28.92 .2403 47 3-10-0 0.2308 0.300 39 86.75
46 Vermont 28.10 .2355 50 1-10-2 0.1538 0.182 20 129.3
47 Bentley 23.53 .2069 40 5-11-0 0.3125 0.455 51 49.20
48 Alabama Huntsville 23.26 .2051 49 3-18-1 0.1591 0.189 29 110.5
49 Air Force 22.14 .1976 43 3-10-1 0.2500 0.333 46 60.88
50 Holy Cross 20.31 .1851 43 4-12-0 0.2500 0.333 49 56.41
51 Ferris State 5.272 .0577 51 0-23-1 0.0208 0.021 23 126.5

Key

  • RRWP: Round Robin Winning Percentage. What your theoretical winning percentage would be if you played every other team, one time each.
  • Ratio: The Ratio of wins to losses (as opposed to Win %, which is wins divided by games).
  • SOS: Strength of Schedule
  • **Win Ratio is infinite

Basic Explanation

KRACH — or “Ken’s Ratings for American College Hockey” — is the implementation for college hockey of a sophisticated mathematical model known as the Bradley-Terry rating system, first applied to college hockey by a statistician named Ken Butler.

This method is based on a statistical technique called logistic regression, in essence meaning that teams’ ratings are determined directly from their won-loss records against one another. A key feature of KRACH is that strength of schedule is calculated directly from the ratings themselves, meaning that KRACH, unlike many ratings (including RPI) cannot easily be distorted by teams with strong records against weak opposition.

The ratings are on an odds scale, so if Team A’s KRACH rating is three times as large as Team B’s, Team A would be expected to amass a winning percentage of .750 and Team B a winning percentage of .250 if it played each other enough times. The correct ratings are defined such that the "expected" winning percentage for a team in the games it’s already played is equal to its "actual" winning percentage.

An alternative definition of a team’s KRACH rating is as the product of its Winning Ratio (winning percentage divided by one minus winning percentage) with the weighted average of its opponents’ KRACH ratings. (The definition of the weighting factor makes this equivalent to the first definition of the KRACH ratings.) In addition to KRACH and RRWP, the table above lists each team’s Winning Percentage, Winning Ratio and Strength of Schedule (the aforementioned weighted average of their opponents’ KRACH ratings).

(Note on the calculation: KRACH requires all teams to have a winning percentage below 1.000 for the calculation to be made. Until all teams in a gender and division have at least a loss or a tie, our calculation adds a single “fictitious tie” to all teams' results.)

KRACH is provided for entertainment purposes only and is not used in any official way, nor is it endorsed by USCHO.com.