ken and wayne (and others)
Thanks for some fascinating reading that (by a loing shot) beats
grading exams. Questions come to mind.

As wayne correctly points out, the important part is the 11 to 20
range because these are the teams that are probably duking it out for
the last few slots in the NCAA tournament.  That would be...

                            KRACH  CHODR    RPI   HEAL  RHEAL Median
 Michigan                      10      9     14     14     10     10
 Boston University              9     18      7     10     12     10
 Minnesota                     12     11     12     15     13     12
 Harvard                       11     14     11     12     19     12
 St. Cloud State               14     13     10     13      8     13
 Dartmouth                     13     26     13      9     11     13
 Miami                         16     10     15     11     17     15
 Notre Dame                    17     16     16     17     15     16
 Merrimack                     20     29     17     18     16     18
 Northern Michigan             22     15     24     16     18     18
 Denver                        18      8     22     19     23     19
 Yale                          19     21     18     25     31     21

of these, Yale is off by 10 in RHEAL, the only other big differences are in
CHODR

> > Observed results "predicted" by system and conference
> >
> >            n KRACH CHODR   RPI  HEAL RHEAL
> > cc        66    51    53    51    53    53
> > ch        13     9     6     7     8     8
> > ec        43    35    33    34    32    30
> > he        34    28    24    27    28    28
> > ma        46    37    30    37    31    33
> > nc       166   140   130   134   127   136
> > wc        43    36    33    36    36    36
> > all      411   336   309   326   315   324

are any of these predictions, or the rankings themselves for that
matter, statistically significant at some level or are we just seeing
minor random fluctuations that aren't significant?

what would really be interesting is to look at the old RPI and the NEW
rpi.  Were I at the office running my roman version of ten windows, i
could set the two side by side and draw inferences.

Also would be the question of whether the changes to PWR are
significant.  Yes, i know, ir is really significant to a team that is
in under one and out under the other


charlie shub   University of Colorado at Colorado Springs
[log in to unmask]               http://cs.uccs.edu/~cdash
(719) 262-3492                  (fax) 262-3369