Monday, February 25, 2013
Spotting a biased study
James does excellent work. So, I don't feel (too) bad pointing out when he presents an obviously biased research piece. In his quest to standardize two distributions, he didn't stop to ask if he should standardize it as he did. When the most underrated players also happen to be the best player, then perhaps simply using z-scores is not the right way to do it.
We first need to see what kind of distribution the EloRater generates and what kind of distribution the Hall Rating generates. If they are not similar, then you can't standardize them the same way. Maybe you need to take the square or the square root of one or the other to get more comparable distributions, I don't know.
But, as soon as you see a list filled with the best players, that's your indicator that you've got a biased study. Thanks to James for letting me be his foil.?
Recent comments
Older comments
Page 1 of 150 pages 1 2 3 > Last ›Complete Archive – By Category
Complete Archive – By Date
FORUM TOPICS
Jul 12 15:22 MarcelsApr 16 14:31 Pitch Count Estimators
Mar 12 16:30 Appendix to THE BOOK - THE GORY DETAILS
Jan 29 09:41 NFL Overtime Idea
Jan 22 14:48 Weighting Years for NFL Player Projections
Jan 21 09:18 positional runs in pythagenpat
Oct 20 15:57 DRS: FG vs. BB-Ref
Apr 12 09:43 What if baseball was like survivor? You are eliminated ...
Nov 24 09:57 Win Attribution to offense, pitching, and fielding at the game level (prototype method)
Jul 13 10:20 How to watch great past games without spoilers