View Single Post
  #4   Spotlight this post!  
Unread 25-04-2014, 11:05
MikeE's Avatar
MikeE MikeE is offline
Wrecking nice beaches since 1990
no team (Volunteer)
Team Role: Engineer
 
Join Date: Nov 2008
Rookie Year: 2008
Location: New England -> Alaska
Posts: 381
MikeE has a reputation beyond reputeMikeE has a reputation beyond reputeMikeE has a reputation beyond reputeMikeE has a reputation beyond reputeMikeE has a reputation beyond reputeMikeE has a reputation beyond reputeMikeE has a reputation beyond reputeMikeE has a reputation beyond reputeMikeE has a reputation beyond reputeMikeE has a reputation beyond reputeMikeE has a reputation beyond repute
Re: Statistical Predictions

Quote:
Originally Posted by Basel A View Post
I've been doing it for several years, and this year it's been the worst by far. The game could hardly be more interdependent, which makes any OPR-based predictions bunk. Also, I should note that I've generally found Most Recent OPR to be a better predictor than Max OPR.
Basel gets at the core of the issue for this year's game. The independence assumption inherent in OPR-like regressions doesn't model a game where a plurality of points scored are from cooperation between alliance members.
Unfortunately the data from matches is too sparse to model interactions between specific teams, so we would have to use more advanced techniques (e.g. clustering teams into equivalence classes) which brings an additional set of approximations.
__________________
no stranger to the working end of a pencil