View Single Post
Old
08-07-2013, 08:17 PM
  #106
Dr Quincy
Registered User
 
Dr Quincy's Avatar
 
Join Date: Jun 2005
Country: United States
Posts: 14,847
vCash: 500
Quote:
Originally Posted by habsfanatics View Post
It seems most of hard time understanding probability, what is meant by these articles is that if the play continues the way it has for the past 48 games then results will most likely be this. There's always a possibility that leafs, flames, oilers, sabres improve their possession games, but if they don't, this is the closest educated guess you can make.

If everything stays the same, or even close to the same as far as possession, he'll be close to bang on IMO.

If the newly acquired players do nothing to improve the teams underlying metrics, ie increase possession, then they'll have little or nothing to do with the prediction.
The problem is, the prediction would have said the same thing after 20 games last year, and 30 and 40, and if after another 30 games this year, if those teams still are being "lucky" and winning more than this prediction expects, the prediction will expect them to start losing. When the prediction is wrong it's just "Oh that's random variance or luck, and the team will regress to the mean" and that can be said at any point in time. Yes as soon as one of those teams has a bad record I'm sure some proponents will say, "See, the model is right!"

It would be great if every time I looked like I was wrong I could just say, "Yeah but eventually I'll be right." And then at any moment I look like I'm right I can just say, "Yup, I'm right."

I'm not saying all or most people espousing advanced stats do this (and I'm not even against the advanced stats) but it's something I have seen by some people who have become slaves to certain statistics.

Dr Quincy is offline   Reply With Quote