Sender: |
|
Subject: |
|
From: |
|
Date: |
Mon, 14 Feb 1994 22:12:38 PST |
Reply-To: |
|
Parts/Attachments: |
|
|
The most notable move this week was that of Harvard; their two wins
against less-than-frightening opposition (Colgate and Cornell) coupled
with losses by CC and NMU moved them up into 3rd. Further down the list,
Brown (with wins against the same two opponents as Harvard) and
Bowling Green (two wins against Kent) both moved up four places.
Rank Last Team W L T Rating Week's results
===================================================================
1. (1) Michigan 27- 2- 1 12.381
2. (2) Boston U 19- 7 11.260
3. (6) Harvard 15- 3- 2 11.078 31:W 39:W
4. (3) Colorado Coll 19- 9- 2 10.999 7:W 7:L
5. (5) Minnesota 17- 9- 4 10.964 30:T 30:W
6. (4) Northern Mich 18-11- 1 10.926 18:W 18:L
7. (7) Wisconsin 18-11- 1 10.909 4:L 4:W
8. (9) Northeastern 16- 7- 5 10.850 26:W
9. (10) Lake Superior 19- 9- 3 10.837 11:W 11:T
10. (8) Mass-Lowell 16- 6- 7 10.830 15:T 15:T
11. (13) Michigan State 16- 9- 4 10.681 9:L 9:T
12. (11) St Cloud 15-10- 3 10.659 24:W 24:L
13. (14) W Michigan 17- 9- 2 10.641 33:W 33:W
14. (12) New Hampshire 16-11- 1 10.583 27:L
15. (15) Maine 14-11- 3 10.510 10:T 10:T
16. (16) RPI 14- 6- 3 10.430 43:W 28:T
17. (21) Brown 12- 6- 3 10.321 39:W 31:W
18. (19) Alaska-Anchorage 12-14- 2 10.295 6:L 6:W
19. (18) Miami 14-11- 1 10.227 36:L 32:W
20. (20) Alaska-Fairbanks 15-10 10.224
21. (17) Denver 13-15- 2 10.217 29:L 29:L
22. (26) Bowling Green 13-12- 2 10.128 34:W 34:W
23. (22) Boston College 11-12- 3 10.115
24. (23) Minnesota-Duluth 11-16- 3 10.114 12:L 12:W
25. (25) Clarkson 11- 7- 4 10.062 42:W 35:W
26. (24) Providence 11-13- 3 10.024 8:L
27. (30) Merrimack 10-13- 2 9.897 14:W
28. (27) Vermont 10- 8- 5 9.863 38:T 16:T
29. (32) Michigan Tech 9-19- 5 9.828 21:W 21:W
30. (28) North Dakota 8-19- 3 9.816 5:T 5:L
31. (29) Colgate 10-10- 2 9.684 3:L 17:L
32. (31) Ferris State 10-19- 1 9.569 37:L 19:L
33. (34) Notre Dame 7-19- 4 9.285 13:L 13:L
34. (33) Kent 9-19- 2 9.284 22:L 22:L
35. (35) Princeton 7-10- 3 9.222 40:W 25:L
36. (39) Ill-Chicago 7-21- 2 9.157 19:W 37:T
37. (40) Ohio State 4-15- 5 9.114 32:W 36:T
38. (38) Union 6- 9- 3 9.112 28:T 43:W
39. (37) Cornell 4-12- 5 9.017 17:L 3:L
40. (36) St Lawrence 8-16 8.876 35:L 42:L
41. (41) Air Force 4-14 8.302
42. (43) Yale 4-17 8.160 25:L 40:W
43. (42) Dartmouth 3-17- 1 8.138 16:L 38:L
44. (44) Mass-Amherst 1- 6 7.792
45. (45) Army 1-12 7.059
-----------------------------------------------------------
KRACH works along the following lines:
The key is the relationship between ratings and probability. Given the
ratings of two teams, first work out the difference d. The probability
of the higher-rated team winning a game on neutral ice is then:
Rating difference Probability
0.0 0.5
0.2 0.55
0.5 0.62
1.0 0.73
1.5 0.82
2.0 0.88
3.0 0.95
4.0 0.98
5.0 0.99
(or, as a formula: prob=1/(1+exp(-d))).
The ratings are then chosen so that the observed win percentage for each
team is equal to the expected win percentage, which is the average win
probability over all the team's opponents. The better a team's
opponents, the fewer games they will be expected to win.
As a result, a team can achieve a high rating by doing well against
average opposition, or by doing averagely against good opposition.
--
Ken Butler
[log in to unmask]
|
|
|