From Russell Carleton at Baseball Prospectus on May 6, 2013:
Two weeks ago in this space, I asked what a good pitching coach—someone like noted magician Leo Mazzone—is worth to a major-league team. I came up with an estimate that Mazzone might have been worth four wins to the Braves (and Orioles) per year during his tenure.
Well, what about a hitting coach?
Warning! Gory Mathematical Details Ahead!
The nice part about this article is that I took my syntax for the pitching coach one and did a find-and-replace for the word “pitching” and replaced it with “hitting.”
I used the same basic method as before, but to recap:
- I studied the 1993-2012 seasons.
- The hitter played for the same team all year, and that team had the same hitting coach all year. If he was traded, or the team changed hitting coaches in the middle of the season, the hitter was assigned to a blank hitting coach. Also, the hitter needs to have operated under more than one hitting coach in his career.
- Only hitting coaches who had 10 qualified batter-seasons were included (hitter needed a minimum of 250 PA)
- Figures are park-neutralized to the best that I was able and era-adjusted to 2012 levels. I calculated rates of seven outcomes: strikeouts, walks, hits-by-pitch, singles, doubles/triples, home runs, and outs on balls in play.
- AR(1) covariance matrix for player results pegged to the calendar year
- Fixed effect for age (to set a general aging curve)
- Fixed effect for hitting coaches (which is what we will look at).
- Through all this, we create a model that controls for what the hitting coach had to work with (the model knows that certain hitting coaches had a team full of good/bad hitters), park, era, and age.
Read the full article here: http://www.baseballprospectus.com/article.php?articleid=20474
Originally published: May 6, 2013. Last Updated: May 6, 2013.