More NBA spatial data

Adrian the Canadian — my designated Deadspin trawler — sent me an interesting graphic by Kirk Goldsberry and Matt Adams showing the highest percentage shooters from various regions of the court. You might recall that Goldsberry presented similar work at the Sloan Sports Analytics Conference in March (runner up for the research award). My take on this work is that, while interesting and impressive in terms of data, much of the spatial variation in shooting could be explained by factors other than location-specific shooting ability (this will sound familiar if you read my post yesterday on player tracking data).

First, random chance is an issue, especially when trying to identify the best shooters at each location. I think Goldsberry requires a certain number of shots for inclusion at each spot, but he doesn’t do the statistical analysis to determine whether the differences he presents are statistically significant (i.e., large enough such that they are probably not due to chance variation). His big surprise — Rondo leading the league in one mid-range zone — is likely based on a fairly small sample of shots.

Second, defensive position is missing from the analysis. A big red flag for this one is that Durant, at only 40% shooting, leads in the three point zone just to the shooter’s right at the top of the key. Every other three point zone has a guy over 50%. Unless there’s something challenging for right handers about that spot, I’m guessing this is due to differences in shot quality. For example, that may be a common launching pad for right handed guards in the pick and roll, which will often be a contested three. Adrian suggested that shooting guards often end up in that area, especially at the end of the shot clock, and heave up tough, well-guarded shots (Kobe . . .). For some reason, it’s probably uncommon for a well-spaced team to put a guy there for an easy three off a kick out or swing pass.

When and how a player gets the ball might make a difference too (under pressure at the end of the shot clock, off the dribble or from a pass, off a practiced set play or a broken play, etc.). The point is, the differences in field goal percentage that Goldsberry presents could be due to many things, and the strategy implications differ depending on the explanation. I don’t think anyone would tell you to let Ray Allen shoot wide open threes, even though Goldsberry shows he has a very cold area in his paper. And, even after accounting for those factors, remaining differences could just be random chance. We need some error bars on those numbers!

Advertisements

2 responses to “More NBA spatial data

  1. I agree 100%. It seems nice as a paper but it doesn’t hold up under any real statistical scrutiny. Another big difference that isn’t measured is the difference in offensive schemes. A player may be identified as having a strong area, but really the offense sets it up for him to get easier shots from there. This would reflect more on the team than the player.

  2. Yes, exactly. Because of issues like that, you can’t use this much for strategy.

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out / Change )

Twitter picture

You are commenting using your Twitter account. Log Out / Change )

Facebook photo

You are commenting using your Facebook account. Log Out / Change )

Google+ photo

You are commenting using your Google+ account. Log Out / Change )

Connecting to %s