Never Apologize, Never Explain 2014-15

The predictions use these metrics, described below:

Metric Definition
RS Prior ECAC regular season
PS Prior ECAC post-season
Imp Second-half improvement
WRet Returning strength
Avg10 Traditional program strength

 

The Metrics

RS

RS is each team's points in the prior ECAC regular season:

RS  
Brown 17  
Clarkson 24  
Colgate 29  
Cornell 26  
Dartmouth 16  
Harvard 16  
Princeton 8  
Quinnipiac 28  
RPI 21  
SLU 18  
Union 37  
Yale 24  

PS

PS is the number of upset (lower seed) advances (+1) or eliminations (-1) in the previous season's ECAC tournament.  The consolation game is ignored.

The upsets in the last season's ECAC tournament were:

PS  
Brown 0  
Clarkson 0  
Colgate 0  
Cornell 0  
Dartmouth +1  
Harvard 0  
Princeton 0  
Quinnipiac 0  
RPI -1  
SLU 0  
Union 0  
Yale 0  

 

Imp

Imp is the difference in points gained in the second half (games 12-22) minus the first half (games 1-11) of the prior ECAC regular season, divided by 2 (and rounded down).  A positive Imp indicates the team had a better second half:

Pts 2nd 1st Diff Imp  
Brown 17 6 11 -5 -2  
Clarkson 24 8 16 -8 -4  
Colgate 29 14 15 -1 0  
Cornell 26 13 13 0 0  
Dartmouth 16 12 4 8 +4  
Harvard 16 9 7 2 +1  
Princeton 8 2 6 -4 -2  
Quinnipiac 28 11 17 -6 -3  
RPI 21 12 9 3 +1  
SLU 18 11 7 4 +2  
Union 37 19 18 1 0  
Yale 24 13 11 2 +1  

 

WRet

WRet captures how much of last year's players' contribution returns (or has been lost to graduation or early departure).

First the returning strength of three subcomponents is calculated for the team's "significant" players, as defined here:

We then weight these numbers by their position's contribution to the team at full strength (3 forwards, 2 defensemen, and 1 goaltender), and multiply the result by 3 to approximate the dispersion from prior Returning Strength metrics:

WRet = (3*RetF + 2*RetD + RetG)/6

The team breakdowns of  Returning Players are shown below.

All of last year's significant seniors are assumed non-returning, unless otherwise noted.  The seniors from last season returning are:

The following significant players with eligibility remaining are not returning:

Backup Data:

Returning (Y) and Non-Returning (N) players by team by position.  Early departures in italic.

  RetF RetD RetG WRet
  Brown 0.88 0.26 0.66 0.639
  Ret 114 10 1234
  Total 129 38 1880
  1 35 Y 17 N 1234 Y
  2 32 Y 10 Y 646 N
  3 29 Y 6 N
  4 15 N 5 N
  5 10 Y
  6 8 Y
 
  Clarkson 0.27 1.00 1.00 0.637
  Ret 39 54 2564
  Total 142 54 2564
  1 32 N 17 Y 1402 Y
  2 28 N 14 Y 1043 Y
  3 25 Y 13 Y 119 Y
  4 23 N 10 Y
  5 20 N
  6 14 Y
 
  Colgate 1.00 1.00 0.76 0.960
  Ret 165 57 1803
  Total 165 57 2369
  1 33 Y 20 Y 1683 Y
  2 30 Y 19 Y 566 N
  3 28 Y 9 Y 120 Y
  4 28 Y 9 Y
  5 26 Y
  6 20 Y
 
  Cornell 0.62 0.91 0.04 0.621
  Ret 78 40 72
  Total 125 44 1954
  1 27 N 24 Y 1882 N
  2 24 Y 8 Y 72 Y
  3 24 Y 8 Y
  4 20 N 4 N
  5 16 Y
  6 14 Y
 
  Dartmouth 1.00 1.00 0.87 0.979
  Ret 111 43 1790
  Total 111 43 2055
  1 29 Y 13 Y 1454 Y
  2 21 Y 11 Y 336 Y
  3 19 Y 10 Y 265 N
  4 16 Y 9 Y
  5 13 Y
  6 13 Y
 
  Harvard 1.00 1.00 0.53 0.922
  Ret 106 28 990
  Total 106 28 1870
  1 22 Y 10 Y 970 Y
  2 20 Y 8 Y 880 N
  3 20 Y 6 Y 20 Y
  4 15 Y 4 Y
  5 15 Y
  6 14 Y
 
  Princeton 0.53 0.59 0.51 0.549
  Ret 48 16 968
  Total 90 27 1912
  1 21 N 11 N 956 Y
  2 21 N 9 Y 944 N
  3 13 Y 4 Y 12 Y
  4 12 Y 3 Y
  5 12 Y
  6 11 Y
 
  Quinnipiac 0.50 0.66 1.00 0.637
  Ret 109 43 2435
  Total 218 65 2435
  1 43 Y 22 N 2409 Y
  2 42 N 17 Y 26 Y
  3 38 N 14 Y
  4 38 Y 12 Y
  5 29 N
  6 28 Y
 
  RPI 0.32 0.59 1.00 0.522
  Ret 53 24 2236
  Total 165 41 2236
  1 43 N 12 Y 2113 Y
  2 30 N 12 Y 103 Y
  3 27 Y 10 N 20 Y
  4 26 N 7 N
  5 26 Y
  6 13 N
 
  SLU 0.29 0.56 0.18 0.361
  Ret 52 51 423
  Total 181 91 2301
  1 57 N 36 Y 1878 N
  2 37 N 33 N 300 Y
  3 35 N 15 Y 123 Y
  4 18 Y 7 N
  5 17 Y
  6 17 Y
 
  Union 0.59 0.27 1.00 0.554
  Ret 129 27 2530
  Total 217 100 2530
  1 50 N 39 N 2080 Y
  2 41 Y 34 N 425 Y
  3 38 N 16 Y 25 Y
  4 34 Y 11 Y
  5 31 Y
  6 23 Y
 
  Yale 0.48 0.72 1.00 0.646
  Ret 63 47 2002
  Total 132 65 2002
  1 37 N 20 Y 1764 Y
  2 32 N 18 N 238 Y
  3 18 Y 16 Y
  4 16 Y 11 Y
  5 16 Y
  6 13 Y

Summary:

  RetF RetD RetG WRet  
Brown .88 .26 .66 .639  
Clarkson .27 1.00 1.00 .637  
Colgate 1.00 1.00 .76 .960  
Cornell .62 .91 .04 .621  
Dartmouth 1.00 1.00 .87 .979  
Harvard 1.00 1.00 .53 .922  
Princeton .53 .59 .51 .549  
Quinnipiac .50 .66 1.00 .637  
RPI .32 .59 1.00 .522  
SLU .29 .56 .18 .361  
Union .59 .27 1.00 .554  
Yale .48 .72 1.00 .646  

Avg10

Avg10 measures traditional program strength, by taking the team's mean number of Points over the prior 10 seasons.  This will be used to compute the expected Incoming factor.

 

Backup Data:

Brn Clk Col Cor Drt Hvd Prn Qpc RPI SLU Uni Yal  
2005 20 16 31 38 28 32 14 13 19 17 7  
2006 11 20 30 29 30 27 17 17 22 25 22 14  
2007 16 30 17 24 27 22 22 24 17 33 15 17  
2008 15 33 21 25 15 27 28 22 15 16 25 22  
2009 10 20 17 29 24 24 28 21 13 26 20 32  
2010 16 11 26 31 17 17 18 22 23 23 28 32  
2011 18 19 11 24 26 15 24 19 24 13 36 35  
2012 14 22 23 30 19 25 16 23 17 21 32 22  
2013 20 19 15 19 22 14 20 37 27 22 24 25  
2014 17 24 29 24 16 16 8 28 21 18 37 24  
   
Pts 157 214 220 273 224 219 195 213 192 216 256 230  
Avg 15.700 21.400 22.000 27.300 22.400 21.900 19.500 23.667 19.200 21.600 25.600 23.000  

Summary:

Avg10  
Brown 15.700  
Clarkson 21.400  
Colgate 22.000  
Cornell 27.300  
Dartmouth 22.400  
Harvard 21.900  
Princeton 19.500  
Quinnipiac 23.667  
RPI 19.200  
SLU 21.600  
Union 25.600  
Yale 23.000  

Putting it All Together

From these independent metrics, we now generate several calculated metrics:

Metric Name Definition Calculation
Prior "Prior Season" Total of prior season metrics RS + PS +Imp
Ret "Returning Factor" Portion of current value from returnees WRet * Prior
WInc "Weighted Incoming" Pct of incoming value 1 - WRet
Inc "Incoming Factor" Portion of current value from incoming WInc * Avg10
Nieu "New Predictor" Sum of veteran and incoming factors Ret + Inc
Pred "Prediction" Predicted order of finish Rank order of Nieu

All but the last of these calculated metrics are just convenient conceptual groupings -- the final metric, Nieu, could be calculated directly from the independent metrics.  But we'll sacrifice brevity for clarity of expression (and check our work) by spelling them out in the table below:

 

RS PS Imp Prior WRet Ret Avg10 WInc Inc Nieu Pred  
Brown 17 0 -2 15 0.639 9.585 15.700 0.361 5.668 15.253 11  
Clarkson 24 0 -4 20 0.637 12.740 21.400 0.363 7.768 20.508 8  
Colgate 29 0 0 29 0.960 27.840 22.000 0.040 0.880 28.720 2  
Cornell 26 0 0 26 0.621 16.146 27.300 0.379 10.347 26.493 3  
Dartmouth 16 1 4 21 0.979 20.559 22.400 0.021 0.470 21.029 6  
Harvard 16 0 1 17 0.922 15.674 21.900 0.078 1.708 17.382 10  
Princeton 8 0 -2 6 0.549 3.294 19.500 0.451 8.795 12.089 12  
Quinnipiac 28 0 -3 25 0.637 15.925 23.667 0.363 8.591 24.516 4  
RPI 21 -1 1 21 0.522 10.962 19.200 0.478 9.178 20.140 9  
SLU 18 0 2 20 0.361 7.220 21.600 0.639 13.802 21.022 7  
Union 37 0 0 37 0.554 20.498 25.600 0.446 11.418 31.916 1  
Yale 24 0 1 25 0.646 16.150 23.000 0.354 8.142 24.292 5