View Single Post
Old 03-06-2015, 09:15 PM   #99
Flames Fan, Ph.D.
#1 Goaltender
 
Flames Fan, Ph.D.'s Avatar
 
Join Date: Mar 2006
Location: Underground
Exp:
Default

Quote:
Originally Posted by Quincy Egg View Post
Except we ended up being right about the Avalanche, and most of us realize what the definition of an adequate sample size is.
This is very muddled thinking.

The whole point of using these numbers is to construct models that reliably predict winning and losing trends. There is no "ended up being right" in a quantitative model. In the case of the Avalanche, the model clearly failed last year.

Real life is not there to fit the model, the model is there to fit the data.


Edit: Apologies to all who made the same point before me. I'm the world's slowest post crafter, bar none.

Last edited by Flames Fan, Ph.D.; 03-06-2015 at 09:27 PM.
Flames Fan, Ph.D. is offline   Reply With Quote
The Following 10 Users Say Thank You to Flames Fan, Ph.D. For This Useful Post: