View Single Post
12-11-2012, 07:33 PM
Czech Your Math
Registered User
Czech Your Math's Avatar
Join Date: Jan 2006
Location: bohemia
Country: Czech_ Republic
Posts: 4,845
vCash: 500
I think it would be very difficult to determine just how good the backups were, for many of the reasons given: small sample sizes, games played not always random, etc. Players also change in ability due to advancement, age, injuries, etc., so being X % below Goalie Y's SV% in one season may not be the same as in another season.

It might be better to use regression somehow, with a dependent variable of SV% (% or %points above/below avg.) and independent variables such as Shots Against per Game (or amount above/below avg.), Shot differential (Corsi?), PK% (or amount above/below avg.), etc.

Czech Your Math is offline   Reply With Quote