Some economists from McGill University and UT-Austin just wrote a paper (Parsons et al., 2007) that purports to find racial bias in baseball umpiring, specifically ball/strike calls on pitches at which the batter does not swing. Here’s the payoff quote:

The highest percentage of called strikes occurs when both umpire and pitcher are White, while the lowest percentage is when a White umpire is judging a Black pitcher. What is intriguing is that Black umpires judge Hispanic pitchers harshly, relative to how they are judged by White and Hispanic umpires; but Hispanic umpires treat Black pitchers nearly identically to the way Black umpires treat them. Minority umpires treat Asian pitchers far worse than they treat White pitchers.

(Personally, I’m not sure I agree that the apparent bias of black umpires against hispanics and vice versa is more (or less) intriguing than the apparent bias of whites against blacks. But Tom Lehrer’s National Brotherhood Week comes to mind.)

The authors attempt to control for many obvious confounders, by including fixed effects for pitchers and umpires and home and away, and controlling for inning and other important variables. Oddly, they do not appear to have controlled for the race of the batter (or, rather, whether the batter and umpire are the same race), which I would have thought might have an effect bigger than the race of the pitcher.

Quantitatively, the results “indicate that a given called pitch is approximately 0.34 percentage points more likely to be called a strike if the umpire and pitcher match race/ethnicity, a statistically significant result. [With over 1.5 million pitches in the database, an effect a great deal smaller than this would still be “statistically significant” –Phil] Excluding (as we do) pitches where the batter swings, the likelihood that a given pitch is called a strike is 31.8 percent. Thus when the umpire matches the pitcher’s race/ethnicity the base rate of called strikes rises by slightly more than 1 percent compared to the result if there is no match. At first, this effect may seem trivial, affecting on average less than one pitch per game.”

Selectively mis-calling carefully selected high-leverage pitches could be very damaging, but obviously, if one or two extra randomly selected pitches in a game are called either in favor or against a pitcher there is very unlikely to be an impact on the game outcome, or indeed even on the outcome of the at-bat. On the other hand, the authors suggest that over the course of a full season, a non-white pitcher would be expected to lose about 0.6 more home games than if he were white and pitched identically; based on this and a back-of-the-envelope salary calculation, they roughly estimate the effect of “discrimination” to cost non-white pitchers somewhere in the neighborhood of $1 million. (The effect of non-white umpires judging white pitchers is much smaller because there are not very many non-white umpires).

The paper has a (depressingly) standard selection collection of tabulated regression coefficients and bad graphics.

This report has already been picked up by the mainstream media. King Kaufman’s comment:

Hot on the heels of a study that found a slight racial bias in the work of NBA referees comes one that finds the same thing in the work of major league baseball umpires.
Next they’ll be telling us there’s racial bias in law enforcement. I mean, where does it end?