Wednesday, September 23, 2015
Predicting arbitration salaries
?I was surprised a few years ago with Matt's arb model (henceforth being used at MLB Trade Rumours) that showed that the salary was dependent on the past salary of the player. Specifically, that you can have two pitchers with an identical performance in 2014-2015, but one having a 2015 salary of 10MM$ and another with a salary of 5MM$, and when it came time for the 2016 arbitration, that the player with the 10MM$ salary in 2015 would end up with a much higher salary in 2016. This has been the only thing I've learned in all my readings of salary arbitration.
Rich offers a simpler solution that bypasses what we learned from Matt. It's also not clear whether he only looks at one season, two years, two seasons (i.e., could be three years if you have a missing year), or career to that point.
But one thing that you can't do is declare anything to be accurate in terms of "prediction" if the data you are "predicting" was used to create your regression! That's a recipe for overfitting. If Rich wants to compete for best prediction, then make the prediction BEFORE SEEING THE RESULTS (i.e., before the salaries are published). That means, we'll wait a few months to get our answer.
Recent comments
Older comments
Page 1 of 151 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