The buzz in my corner of the bastketball world is (a) the GS Warriors (!) and (b) NBA refs. Writing in the Wednesday New York Times, Alan Schwarz reported on a study by Justin Wolfers and Joseph Price about fouls called by referees in the National Basketball Association games. In their paper, “Racial Discrimination Among NBA Referees,” Mr. Wolfers and Price analyzed a large data set (600K foul calls) covering many years (1991-92 through 2003-4 seasons) and found a slight but clear bias. Mr. David Stern disagrees with these findings.
According to Mr. Price and Mr. Wolfers, as the number of white officials on a crew increases from none to three, black players were called for 0.12-0.20 more fouls per normal game (games are 48 min; overtime games add 5 min per overtime period) played; this represents an increase of 2.5 to 4.25%. There was a smaller but significant effect of more fouls called on White players when the officiating crew included more Blacks. According to Mr. Schwarz, Mr. Stern reviewed the NBA’s data on referees and came to a different conclusion.
N.B.A. Commissioner David Stern said in a telephone interview that the league saw a draft copy of the paper last year, and was moved to do its own study this March using its own database of foul calls, which specifies which official called which foul.
“We think our cut at the data is more powerful, more robust, and demonstrates that there is no bias,” Mr. Stern said.
This AM on National Public Radio’s Morning Edition, Steve Inskeep interviewed Mr. Stern and he reiterated this postion. He claimed that the NBA study was stronger because it did not analyze foul data by referee crews, but by individual referees. Even though the NBA data cover a shorter time period, hence fewer referees, players, minutes, and fouls (and lower statistical power), it would be interesting to conduct the analyses at the level of individuals.
Mr. Stern could go a long way toward solving this matter by simply releasing the NBA data. There are plenty of folks who have sufficient statistical competence to conduct careful analysis of such data (think of the Society for American Baseball Research; see also the Wikipedia entry).
Link to the article by Mr. Schwarz.