More late-game situational statistics

The Harvard Sports Analysis Collective strikes again, and late-game strategy gets another rich set of data to mine.

Last week, author and researcher John Ezek0witz discussed the merits of fouling with a three-point lead at the end of games. The conclusion -- which is not a hard-and-fast rule, but a probability based on hundreds of outcomes -- was that there is no statistical advantage to fouling while up three, given all else is equal. I'd imagine that would make John Calipari (and plenty of other coaches who haven't fouled in that situation, only to give up a game-tying three) feel a little bit better.

This week, Ezekowitz took on another bit of should-I-or-shouldn't-I decision data: Whether the offense should call a timeout on the last possession of a game. Ezekowitz's data (which, again, includes some stuff you may or may not remember from your University of Phoenix statistics seminar):

In the case of teams with the ball when the score is tied, the data clearly show that it is more effective not to call timeout. In my 2009-2010 dataset, 452 teams fit the above criteria. 235 of those teams called timeout, 217 did not. Of the teams that called timeout, only 35.7 percent scored on the subsequent possession. Teams that did not call timeout scored 53.0 percent of the time. A simple two sample t-test with unequal variances shows that this difference is strongly statistically significant (p=0.0002). A logistic regression with timeouts as the independent variable and whether the team scored as the dependent variable showed that calling a timeout was a significant predictor of successfully scoring (p<0.001) and that teams that did not call timeout were twice as likely to score as teams that did.

So, to put it simply, two teams are tied at the end of the game. If the offense calls a timeout, it has less of a chance of scoring than if it simply took the ball out of the hoop and went down the court as quickly as possible. This seems like something coaches should probably know.

Ezekowitz also looked at whether teams on average scored more points by not calling a timeout, and they did.

Teams that called timeout scored an average of 0.773 points per possession whereas teams that did not call timeout scored an average of 1.06 PPP. [...] Thus teams that do not call timeout not only score more often, but also score more points on their possessions than teams that do.

The data is clear, but what's the cause? Ezekowitz hypothesizes that teams on offense know what they plan to do in that short, late-game possession without calling a timeout, whereas the defense stands to benefit most from stopping the game and talking things over. If I had to guess, I'd say the speed of that final possession -- wherein a team races down the court and attacks the defense with a spread secondary set -- is a major advantage to the offense. You hear this in coaching parlance, when a coach calls timeout immediately after a made basket to "set up his defense." Part of that is discussing the specifics of defense. But just as big a part of it is having your defense back and established in the first place.

Anyway, interesting stuff. The HSAC guys are doing yeoman's work, and fans -- not to mention coaches looking for every probabilistic edge at the end of games -- would do well to take notice.