Category Archives: Causal Analysis

Is that a shiny new free agent in your stocking, or an old lump of coal?

NFL playoffs are right around the corner, but ’tis the season for a jolt of baseball excitement too, as teams sign new players. The contracts are getting bigger and bigger, supported by growing MLB revenues. Some of the major signings under the tree this year (more here):

  • Zack Greinke, 6 yrs, $147 million (Dodgers)
  • Josh Hamilton, 5 yrs, $125 million (Angels)
  • B.J. Upton, 5 yrs, $75 million (Rays)
  • Anibal Sanchez, 5 yrs, $80 million (Tigers)

But before you start thinking playoffs, remember that many big deals don’t work out. Who will be nice and who will be naughty this year?

The Old Lumps of Coal

From the list above, Greinke is 29 years old, Hamilton is 31, Upton is 28, and Sanchez is 28. Not many young players are available through free agency, but are these 4 to 6 year deals for 28 to 31 year olds a good idea? I tackled this question with my friend Jeff Phillips for ESPN the Magazine in early October.

Specifically, we wondered if long deals for 30 year olds made more sense during the steroid era, when players could recover, train, and maintain more easily. There are two sides of the coin: (1) how has older player performance changed, and (2) has older player compensation evolved appropriately. We focused on players in the top quarter of the salary distribution, since that’s where the big money is spent. To measure performance, we examined average Wins Above Replacement Player (WARP)* by age during and after the steroid era:

WARP bars

Uh oh. Although performance for all highly paid players has gone down, older “stars” have turned out to be coal indeed. Looking year by year highlights the post-PED age decline. Average WARP for older and younger stars was remarkably similar through the steroid era, but older player WARP Continue reading

Advertisements

New York is Lefty Land

I’m a Tigers fan, so I’m pretty excited about how things worked out the last week. Basically, everything went right for the Tigers and nothing went right for the Yankees.

The only glimmer of hope for the Yankees came in game one. Down 4-0, Ichiro Suzuki hit a line drive homer to right in the bottom of the ninth and Raul Ibanez followed with a pop fly two-run “shot” that might have been an out (or perhaps a double) in most parks. Hope turned to despair when Derek Jeter went down with an ankle injury in the 12th, ending his season, while the Tigers stormed back into the lead. Even worse for the Yankees, their near victory finally knocked Jose Valverde off his closer pedestal. The Tigers should have made that move months ago.

I want to go back to the homers though. It’s no coincidence that both homers went to right field off of left-handed bats. Here are the home/road home run splits for the Yankees lefties in 2012:

Continue reading

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 Continue reading

Player tracking in basketball: not a silver bullet

For anyone who follows quantitative sports analysis, player tracking cameras are not news. Along with the NBA, soccer teams use them (even in the MLS) and rugby teams use them. They give x-y-z coordinates for each player at a high frame rate, which can be processed into a variety of statistics. Many think that this approach will revolutionize sports analysis. I stumbled across an article at ESPN today spreading this view to the masses.

Tracking data can help with many things, but it won’t save analysts from themselves. Here’s a point-counterpoint from the article linked above.

Point: “Paul Pierce averaged 4.5 assists this season, which is pretty good for a scoring wing. But that number doesn’t tell the whole story. According to SportVU, Pierce’s teammates shot a higher percentage after his passes than any other player in the NBA. This shows Pierce is passing at the right time — he’s giving his teammates mostly layups and open shots.”

Counterpoint: Pierce might be making great passes, but it’s just as likely that Pierce plays with better than average shooters or better than average cutters/floor spacers, or that Pierce commands a strong defender Continue reading

The Tank Watch (4/27/2012, final edition)

Earlier this spring, my coauthor Chris and I discovered that NBA teams tank a lot, especially teams in the first or second lottery position. This season, I’ve been tracking team performance before and after playoff-eliminated teams locked in to their lottery position. Once teams clinch their spot, there’s no incentive to tank anymore. We found that teams play much better after clinching. Here’s what things look like this year:

The Tank Watch

As I thought a couple weeks ago, the lockout bunched everyone up this year. There just weren’t enough games for teams to separate at the bottom. Only the Bobcats, Wizards, Timberwolves, Trail Blazers, and Bucks clinched their spots before the season ended. This doesn’t mean that teams weren’t tanking (see my post on the Cavs yesterday), but I can’t really test for tanking in a foolproof way. And, comparing pre/post clinch winning percentage doesn’t identify all tankers, since some teams may make personnel decisions that are irreversible (Exhibit A: the Warriors) and others just get so used to losing or are so terrible that motivation fades (Exhibit B: the Bobcats).

The one team that looks like a tank show for sure is the Wizards, who essentially clinched the second lottery spot a week ago, and rattled off five wins to finish the season. While the Wiz were playing all their stars down the stretch (since they had no reason left to lose), their buddies at the bottom (Cavs, Timberwolves, Warriors) were sitting everyone down or trading them. The big outlier of course is the Hornets, who, due to their league ownership, kept Eric Gordon alive and played GREAT down the stretch. At least it only cost them one spot in the end (they finished tied for third), and Hornets fans can be optimistic about next year with Gordon.

Now that we’re done with all that tanking, let’s get on to the NBA’s second season, where all the best players get to play, all the stadiums are full, and all the teams are above average.

Cavaliers, what have you done?

Yesterday, based on my past research with my buddy Chris, I predicted that the Wizards would take it to the Cavaliers last night. The Wizards were already locked into the 2nd lottery position, while the Cavs could still move up or down. Well, I was right. The Cavs looked good to start the game and then slowly faded away.

Our research shows that teams who haven’t clinched play worse than teams that have. In other words, they tank. However, we haven’t determined how they do it. Are players actually trying to lose, or is it all personnel decisions? Last night’s game gave us some evidence for the latter: Continue reading

Here come the tanks

There’s a lot to decide in the NBA draft lottery still, with six teams bunched between 21 and 23 wins. The most unfortunate of these teams is the Hornets, who have won 62% of their games since they were eliminated from the playoffs on March 31st. They’ve beaten such quality teams as the Nuggets, Rockets, Jazz, and Grizzlies in that stretch — pretty much unheard of for a team in their position — and risen from possibly 2nd in the lottery to a potential tie for 5th (meaning they get the average lottery odds between 5th and 6th places). I’m sure this is due to league ownership (which forced the Hornets to bring back Eric Gordon). It’s a great “natural experiment,” actually, that provides further evidence of tanking by all other (individually owned) teams.

A few teams have clinched their lottery spots already: the Bobcats, Wizards, Timberwolves, and Trail Blazers. My research with my buddy Chris shows that these teams should pick it up now that there’s no reason to tank. Stay tuned for the final Tank Watch in a couple days. There’s a good test match up tonight between the Wiz and the Cavaliers — I expect the Wizards to take it to them. We’ll see if the clinched teams outperform the other playoff eliminated teams over the next two days.