Tuesday, March 25, 2014
Hidden meaning of steals in NBA
Using a WOWY analysis (of the player in the game or not), Ben concludes that steals contain so much information that it makes this statement true:
For example, a player who averages 16 points and two steals per game is predicted (assuming all else is equal) to have a similar impact on his team’s success as one who averages 25 points but only one steal. If these players were on different teams and were both injured at the same time, we would expect their teams to have similar decreases in performance (on average).
It's like the anti-DIPS. Whereas batted balls contain so little information that we want to underweight their results, steals have so much extra information about the ballplayer (things that are not being individually tracked by the remaining statistics, that the steal stat is "asborbing" all this information), that we need to severely overweight it. By a factor of 9 relative to its intrinsic value.
And this really points to the shortcoming of the stats that are being tracked. Presumably, the lack of a decent defense metric is causing the gap, and since defense is important, we overweight the stats that are being tracked. And while we overweight rebounds and assists, it's turnovers, blocks, and especially steals that ?are the beneficiary of this hole in the (public) stat tracking.
Which of course should make you scared, because overweighting the intrinsic value by a factor of 9, is a cause for huge uncertainty. Not all steals are the same, and not all steals tell you the same thing about each player. Maybe for some, it needs to be x5 and another it should be x14. Who knows.
In this case, the regression is not the answer, but simply highlights the problem.
Recent comments
Older comments
Page 1 of 152 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