Monday, June 14, 2010

Is the "Choking" Effect in Sports Real?

There's an interesting discussion over at the Sabermetric Research blog about whether a "choking" effect exists in soccer:

Gier Jordet, a professor at the Norwegian School of Sport Sciences in Oslo, reports that, when the score is tied, penalty kick shooters succeed at a 90% rate. But when the shooter's team is behind by a goal, and presumably there's more pressure, he succeeds only 60% of the time.
I made a similar point in the comments on the SR blog post, but I'm not too surprised that teams perform worse when they're losing.

On average, bad teams spend a larger portion of the game trailing. It's reasonable to assume that they would therefore get more penalty kicks in such situations than good teams would, thus making them overrepresented in the "behind by one goal" sample. If bad teams also have inferior penalty kickers, it's no surprise that they do worse.

Similarly, if your team is playing against an outstanding goalie, you're more likely to be trailing at any given moment than you would be otherwise. In such situations, the outstanding goalie is also more likely to block your penalty kicks.

If we could control for these factors (say, if we had 100 observations of penalty kicks by one team against a certain goalie) and still observed the choking effect, I'd be more convinced.