A "Moneyball" statician predicted Jeremy Lin's success 2 years ago

http://hoopsanalyst.com/blog/?p=487

by GBond • 14 years ago

190 103 14 years ago

hoopsanalyst.com

fluorescentLAMP• 14 years ago

I'm involved in the startup scene for soccer "moneyball" metric development. If anyone has any interest, contact me.

farkob• 14 years ago

I'm interested.

marklabedz2• 14 years ago

Definitely interested. Mind putting your contact info in your profile?

paulschreiber• 14 years ago

A friend of mine is interested in stats for dodgeball. (yes, really!) let me know if you're interested and i'll connect you.

sharksandwich• 14 years ago

Curious to hear what you're up to as well

michael_dorfman• 14 years ago

Wouldn't it be more noteworthy if we weren't able to find one analyst who predicted Lin? With the number of amateur analysts, and the number of players, you'd think that its likely there's a web page somewhere plugging every prospect.

corin_3• 14 years ago

Reminds me of that classic scam of sending out sports (or anything else) predictions to a huge mailing list, and basically AB testing in such a way that after a little time there are at least x% who think your success rate is incredible.

ShabbyDoo• 14 years ago

Yeah. Done historically by stockbrokers making cold calls. Every week, "Now, don't put your money with me just yet. Here's what I'm putting my clients into this week. Just watch Stock XYZ this week to see what happens." If you pick three highly volatile stocks every week, make a lot of calls, and drop the prospects to whom you have given "bad" advice, you'll end-up with a decent sized set of potential clients who think you are a god.

jimmybot4• 14 years ago

How is this anywhere the same?

In a scam, you don't have any way of making any future correct predictions--it's just random. This analyst has a reasoned system that can be tested against past players and against future prospects. Sure, there's going to be someone out there that picks Jeremy Lin. But the trick is, can you correctly identify players who are already known to be good based on their college stats, make the right call on Jeremy Lin, and go forward and continue to make good calls on draft prospects?

I'm not saying this sabermetrician generally makes good calls; I haven't looked. But dismissing his call as the result of a series of Bernoulli trials is completely missing the point.

marknutter2• 14 years ago

That doesn't really detract from the accomplishment. The numbers don't lie. To me it's clear that despite Lin's strong numbers, he wasn't given a chance until now because he didn't fit the archetypal NBA player mold.

lubujackson• 14 years ago

I'd say the impressive thing is the analyst found some figures that seemed to have a high correlation to success, and Lin has panned out pretty close to how he described him. And remember, this is a player who wasn't even drafted, it'd be like finding an analyst tell you Tom Brady has a chance to be a top 5 QB before he was drafted in the 6th round after being a partial backup at Michigan, and backing it up with convincing data.

zheng• 14 years ago

What surprises me most about this story isn't that it happened, but that people still are surprised it works. A data-driven approach will always be better than picking people by how good they "look", etc. Human scouts are biased, make mistakes, and miss plays. Statistics don't lie. The one catch is of course how you analyze those statistics makes all the difference.

GBond2• 14 years ago

Not surprised that most experts(NBA & DI school scouts) don't embrace this because it is easier and safer to go with the typical archetype as opposed to raw stats. Its "human nature" safe in the sense most people will not question if you go with the established archetype. It also devalues the current process of scouting.

An apt quote from the movie Moneyball: "I know you've taken it in the teeth out there, but the first guy through the wall. It always gets bloody, always. It's the threat and not just the way of doing business, but in their minds it's threatening the game. But really what it's threatening is their livelihoods, it's threatening their jobs, it's threatening the way that they do things. And every time that happens, whether it's the government or a way of doing business or whatever it is, the people are holding the reins, have their hands on the switch. They will bet you're crazy. I mean, anybody who's not building a team right and rebuilding it using your model, they're dinosaurs. They'll be sittin' on their ass on the sofa in October, watch the Boston Red Sox win the world series."

gregpilling• 14 years ago

"Sometimes the convincing force is just time itself and the human toll it takes, Kuhn said, using a quote from Max Planck: "a new scientific truth does not triumph by convincing its opponents and making them see the light, but rather because its opponents eventually die, and a new generation grows up that is familiar with it."[1]"

from http://en.wikipedia.org/wiki/Paradigm_shift

jamesaguilar• 14 years ago

Erm, as I understand it most NBA organizations have significant statistics/economics departments. I don't think the practice of going by looks or things of that nature is dominant any more except for sports pundits trying to rationalize events after they have happened.

hyperbovine• 14 years ago

While it's true that sport scouting has traditionally under-relied on data, I wouldn't be so quick write the entire profession off entirely in favor of spreadsheets. Statistics can certainly be made to lie (cf. the book, "How to lie with statistics"), and there are a lot of aspects of human performance that are difficult to quantify. Performance under pressure is the first thing that comes to mind--reliably sinking a buzzer-beating three-pointer is a harder and more valuable skill to possess than just being a good shooter from beyond the line. You could try to quantify "performance under pressure", but a good scout will pick that up intuitively and probably do a better job of it. As always, the truth lay somewhere in the middle; a combination of both data and human input seems to be the best course.

marklabedz2• 14 years ago

The baseball equivalent, clutch hitting, has been kicked around in sabermetric circles for almost as long as Bill James has been writing of baseball's flawed stats and biases of pro scouts.

The "common wisdom" of sabermetrics (if you can call it such a thing) holds that clutch hitting doesn't exist, but many including James, aren't quite ready to completely write it off.

frankdenbow• 14 years ago

Agreed. Theres a startup called NumberFire that essentially focuses on this perspective to serve up information based on sports stats.

toddh2• 14 years ago

How good are the Oakland A's? Not very. So how successful is the data driven approach really? Isn't accepting a single case like this in the NBA as any kind of proof unscientific?

william42• 14 years ago

Didn't the Oakland A's stop being successful precisely because every other team picked up their methods?

tatsuke953• 14 years ago

How good are they? You could try watching the movie,or better yet, read the book. They did well.

Unfortunately for the As (and fortunately for those of us who embrace the statistical analysis of sports) other teams caught up and surpassed their approach. But it's still going on. In every sport. And there is much evidence that it works.

dmbass• 14 years ago

I would expect a complete statistical approach to work great for a sport like baseball where a team is exactly the sum of its players (i.e. most play is individual), but basketball it seems like basketball has so many other factors because you need all 5 players to work together to be effective. A weak player can bring everyone else down and a strong one inflate everyone else's stats. But maybe that just makes the statistics that matter more complex.

mousa2• 14 years ago

They have been getting much more complex. For example many stat geeks have been trying to make one that takes the +/- stats (how well the team does when the player is on the floor in terms of point difference per 100 possessions) and adjusting it based on the +/- of the teammates and opponents that have shared the floor with them. It's definitely more challenging than baseball, but there are a lot of interesting things to try.

tatsuke953• 14 years ago

>"A weak player can bring everyone else down and a strong one inflate everyone else's stats. But maybe that just makes the statistics that matter more complex"

That's exactly it. People often argue that something or other isn't accounted for, but the statistical methods are sophisticated.

Besides, it's not about being perfect, it's about getting an edge.

mousa2• 14 years ago

NBA media and fans are much much more resistant to empirical stuff than baseball. I think it's because the appeal of the game is more about emotions and hype than baseball. There's this feeling that things can't be captured in the numbers, but what they use instead is so inferior for judging players. I mean the Knicks acquired Carmelo Anthony at the cost of all the efficient players on the team. All of the stats guys were very skeptical the media blared on and on about how they would be contenders and they were terrible until this undrafted rookie came along.

Another example, what I've found interesting reading some of the NBA statisticians blogs is this argument about "clutch". Most fans and media insist that Kobe Bryant, a player who shoots a lot of shots at the end of games and makes spectacular shots sometimes is the best closer in the game. Meanwhile almost all statistical evidence points to Chris Paul, a player who runs boring routine plays down the stretch, as by far the best closer in the league in terms of actually winning close games.

Until the NBA stats can predict winners like baseball, the public will always go by the "look." The teams themselves however, are almost all hiring statisticians now.

brildum• 14 years ago

Baseball is easier to predict from statistics when compared to most other sports. Most plays in baseball occur in isolation (relatively).

For example: pitcher vs. batter -- each pitch is essentially a new, repeatable experiment.

In basketball, I would guess that there are very few repeatable experiments. (Different players, strategies, locations, etc). It is a much more fluid game and therefore determining an indicator of success is much more difficult.

kevinkemp2• 14 years ago

Exactly. The key difference is how advanced the statistics that matter are in the different sports. Only very advanced stats will really tell the story in basketball whereas it is much easier to see in baseball with just baseline stats. Most laymen take that to mean that watching games is the only way to tell when, in reality, they just need to get the right stats and formulas.

kasraeg• 14 years ago

it is true stats don't lie. but there is no replacement for the human judgment of personality and dedication. if it was all about stats, allen iverson would have lead the 76ers to multiple championships. THAT'S the importance of personality! thats the importance of showing up for practice. :)

chegra• 14 years ago

Actually, a point guard led team winning a championship is rare. It's the reason people watch Rose[Bulls] with suspect. The last time it was done was with Piston during the Bad Boy's era[late 80s, early 90s]. So, although individual accolades accompany Iverson, I doubt anyone would predict him to win multiple championships without significant help[well except the media].

look_lookatme• 14 years ago

That's a helluva a catch.

At the core, stats tell a story of what a player has done in the past. Projections predict what a player might do based on what comparable players have done in the past. Statistics don't tell the future. They are just one tool of the scouting process.

Plus the models are always evolving. What was considered an indicator of talent 20 years ago might be inferior to the indicator 10 years ago that is actually inferior to what is in vogue today.

Statistics don't lie, but what story do you think they actually tell?

Super_Jambo• 14 years ago

According to 'Thinking Fast and Slow' which I'm currently reading expert predictors of performance are generally worse than even quite simple statistical models. This being due to all the flaws in human decision making - if it's a sunny day, if the player 'looks the part' if the scout happens to view them on a day when they're feeling lucky. It's a very good book, but it suggests that in all fields of prediction you should actually rely on combinations of statistical metrics over expert judgment.

Pretty hard to believe I accept.

tpiddy• 14 years ago

I tend to agree with you, hell i'm basically an analyst by trade.

but for the other side of the argument you should check out mark cuban's post http://blogmaverick.com/2010/10/03/building-teams-using-quan...

ivanzhao• 14 years ago

Noticed the article was written a year ago (May 13, 2010), and Lin went undrafted that year.

minouye• 14 years ago

How is he calculating RSB40? I'm guessing its some sort of weighted average of rebounds, steals, and blocks but I can't find a solid definition.

jcliff85• 14 years ago

(Rebounds + Steals + Blocks) / (40 mins)

jimmybot4• 14 years ago

I know what you mean, but technically, it's: (Rebounds + Steals + Blocks) * (40 mins) / (minutes played)

milhous• 14 years ago

It's spelled 'statistician'.

bretthopper• 14 years ago

Just some background for those not familiar with "Lin-sanity":

- He was a great college player at Harvard but wasn't drafted.

- He was cut by 2 NBA teams before the Knicks picked him up.

- He was probably the 4th point guard on the Knicks depth chart.

- The Knicks have been terrible this year and are currently without their 2 best players (Amare Stoudamire and Carmello Anthony)

- The Knicks have now won 4 straight games with Jeremy Lin playing big minutes (including 3 starts).

- The 89 points he scored in his first three starts (including Friday) got him a historical distinction. They are the most scored by an NBA player in his first three starts since the NBA-ABA merger 1976-77.

- Everyone loves him.

WillyF• 14 years ago

If you go by the WP48 stat, Amare is actually the Knicks' second worst player and Carmelo is their 8th best player. Tyson Chandler is by far their best player, and is currently the second best player behind LeBron.

http://www.thenbageek.com/teams/nyk

fanboy123• 14 years ago

He's also currently ranked 2nd in PER right behind LeBron James who by most metrics is the most dominant player in the NBA. PER is a metric for player efficiency adjusted for pace and time played etc. Pretty nuts.

http://insider.espn.go.com/nba/hollinger/statistics?&act...

MatthewPhillips• 14 years ago

WP isn't really considered a credible metric in the basketball stat community. It overvalues rebounding; players such as Danny Fortson and Reggie Evans have been ranked in top 5 for WP.

pepdek• 14 years ago

I'd like to add the Knicks gave serious consideration to cutting him from the roster hours before his first start because his 30-day contract was set to expire in a few days.

j-kidd3• 14 years ago

The moral of story here is that if you have an expiring contract, you better hope your next opponent would be the Nets ;)

jwallaceparker2• 14 years ago

Where did you hear this? I follow the Knicks closely and never heard they were considering cutting him.

capkutay2• 14 years ago

Not to mention, he led our basketball team to the state championship in high school, but got little to no recognition from college scouts. I would guess that most state championship winning starting point guards in high school would at least get 1 scholarship offer. Jeremy Lin got none. It just makes his success more shocking/amazing at this point.

ssharp6• 14 years ago

This isn't necessarily true (most state championship winning starting point guards getting scholarships). How big was his high school? Upper division programs (large schools) get significantly more attention than smaller schools.

wisty• 14 years ago

That's insane. It's been suggested he was passed over because he's of Chinese decent. You'd think the teams would be climbing over themselves to get a good player with a Chinese name, because that's a way to get tens (or hundreds) of millions of Chinese fans.

He's not the next Yao (since he's American born, for starters), but he'd still be worth a lot purely for the fans he'd draw.

While "hundreds of millions" is often just hyperbolic thinking, Chinese are keener on the NBA than Americans. Unless the world cup (soccer) or Olympics is on, it's the only spectator sport worth speaking of. And Chinese love brand-name goods, and sports memorabilia, though many are forged.

Plus, he's a good player.

jwallaceparker2• 14 years ago

I'm a Knicks fan visiting China right now. Jeremy Lin's game against the Lakers was the lead story on the sports program on television last night. He could catch on here.

ssharp6• 14 years ago

I highly doubt any team passed over him because of his ethnicity. That's insanely counter-productive and something that doesn't happen in modern sports, especially the NBA. Yao Ming was a #1 draft pick. The NBA knows it's strong position in China.

bgaluszka• 14 years ago

> The Knicks have been terrible this year and are currently without their 2 best players (Amare Stoudamire and Carmello Anthony)

... and you could say Baron Davis, their point guard that JL is in place of.

bilbo0s2• 14 years ago

Hmm...

I looked into his stats because I don't pay much attention to the Knicks.

At any rate I think Jeremy Lin is definitely going to have a good deal of trouble succeeding long term. There are a number of concerns there, but by far the biggest is TOs. In each game he's played, he has had the most TOs of any player. You can coach that away but one of two things will happen, his FGs will go up and his ASSTs will go down, or his ASSTs will go up and his FGs will go down. What you want, for a lot of reasons that most of you probably already know, is for the latter to happen. What seems to be happening is the former. There is a reason it is called a Point Guard. That needs to be fixed or other coaches will definitely take advantage of it when it counts.

You say, "well no problem...when Stoudemire and Anthony get back the problem will ameliorate." It may. I don't know. I would have to revisit his stats at that time. If I had to bet, I would bet that it will get better. But other young PGs struggle with the same issue...to the detriment of their teams in my opinion.

I guess what I am saying is that success in basketball, as measured in rings, requires stats optimized for balance and flexibility rather than strength. When Jason Williams finally got to Miami he was a more balanced PG. IIRC, during the 2006 finals he averaged 12 points and 7 ASSTs. Critically, at that point in his career TOs were under control. Jason Williams peaked at, somewhere around 3.5 a game. Jeremy Lin is averaging twice that at least. Not good. And consider, Jason Williams could make some of that up on the back end with steals. Not so much with Jeremy.

So I can see why a lot of statisticians would look at Jeremy Lin and say,"...well with my personnel...I'll have to pass on this guy." Of course if we scour the web we will find one guy who rated him highly, that is the nature of the beast. But there are a lot of good reasons that a lot of good scouts did not rate him highly. And most strategists probably see a lot of those reasons every time he plays.

All that said, Jason Williams, after initially playing a lot like Jeremy, achieved a REALLY good ASST/TO rating. If it wasn't THE highest...it was close. But again, that's the 12 points 7 ASSTs Jason Williams, which is what you want in a PG if you want to get to a ring.

stakecounter• 14 years ago

In response to the turnovers, I want to mention that there are a couple reasons for that.

The first is that he's playing PG and has to handle the ball a lot more than anyone else on the team right now. Combined with his minutes, that's generally going to give you more TO's just because of the amount of time with the ball and the probability of a player of his skill level losing it (although this point doesn't account for other PG's who average way fewer TO's).

Second, he's just started to play a ridiculous amount of minutes over the past week and hasn't had enough time to refine himself yet. Did you watch the first couple weeks of games this season? Because of the lockout this year, there were almost no preseason games and it showed. Turnover rates were extremely high for pretty much every team, so I'm inclined to think that Lin can get his turnovers down throughout the rest of the season assuming they keep playing him.

My last point is a pretty obvious one, but he's still young. A few more years of experience and I expect to see turnovers go down. I watched his 38 point game last night, and while he played pretty amazing, he did have moments where he looked confused and flustered when running the offense.

ncavig• 14 years ago

I agree. Generally with smart basketball players, there TO's go down as they get familiar with the pace and level of play. A comment struck me the other day by an announcer, Lin has never played against 7 footers before. Whether that's true or not, he may have seen a few while at Harvard, but to consistently play against these behemoths has got to be a new feeling. Regardless of skill, it'll still take time to get use to the size and style of the NBA.

What I love about Lin is he is a smart player and a smart person. It's not a surprise to him that he's turned the ball over. Guess what he'll be working on in the future.

dmragone• 14 years ago

Aren't we also talking about a tiny sample size with the Knicks? And one of those games I believe he had 8 turnovers. That could easily be skewing these early numbers.

Is there any evidence of turnover concern from his time at Harvard?

oinksoft• 14 years ago

somewhere around 3.5 a game. Jeremy Lin is averaging twice that at least

In his first four games of real time, he's averaging 4.25 turnovers, 8 assists, and 28.5 points per game. Deron Williams, a premier point guard in his prime, and playing with talent about on par with Lin's right now, is averaging 8.4 assists and 4.22 turnovers per game.

The turnovers might be a touch high, but there wasn't a moment in last night's game where I thought, "oh, this guy's just taking way too many risks." He seems quite solid.

And any fool watching these games knows that Lin's no Jason Williams.

Rajiv_N• 14 years ago

I think you are over-analyzing. Like others have said in this thread, TO's are expected from PG's. While, these stats need to be considered, you should also consider the timing of these turnovers. If his team is up 15 with 1 minute to go and he turns the ball over because he was trying to test a play etc... that TO should not be given the same weight as the others.

I think the most important stat is scoring efficiency (or FG percentage). Against the Lakers yesterday, he was at 56.5% for the game (scoring 38 points). That is commendable given that it is against the Lakers.

weixiyen3• 14 years ago

4 TOs is very low considering his usage rate. The TOs will go down once Melo plays iso.

carguy1983• 14 years ago

HN-related factoid: Jeremy Lin was born in southern CA, grew up in Palo Alto and both of his parents are immigrant engineers.

noelwelsh2• 14 years ago

I love Jeremy Lin as a player and I really hope he succeeds. However, it must be said: Four games does not a statistically significant sample make. Read the NBA Playbook breakdown of his game:

http://nbaplaybook.com/2012/02/08/a-look-at-jeremy-lin/

In summary, he isn't good going left or shooting from distance. So far he hasn't played an elite defensive team. The true test will come if he can sustain his performance over the season and against good defence. Let's hope he does it!

steve8918• 14 years ago

So what if he hasn't played against an elite defensive team. That is irrelevant to determine whether or not he will succeed. How many players would do well against an elite defense team? Probably not a lot, otherwise they wouldn't be an elite defensive team.

No one is saying that he's going to be another Stockton, Nash, Wade (although Magic Johnson did say that Lin reminded him of Stockton and Nash), and he doesn't need to be in order to succeed. If he can keep the caliber of his game up to NBA standards, he can accomplish what he wanted, which is to play in the NBA, and that's all that matters. His performance over the past 4 games is saying pretty strongly that he can play at this level.

Remember, he just played against over 10% of the league already and has been the best player on the court. If the Knicks elite players can get their act together, then Lin only needs to contribute positively in order to maintain a strong career.

noelwelsh2• 14 years ago

You make some good points. Lin has probably already done enough to have a decent NBA career and retire with millions in the bank. However the hype surrounding Lin is that's he more than that. The main point I wanted to make is that four games is not enough data to make that conclusion.

He's certainly lucky to play for D'Antoni, who is just about the only coach in the NBA who'd let a point guard freelance like Lin has. He's also lucky that the Knicks' star players are out so he doesn't have the pressure to just pass them the rock, which wouldn't showcase his skills. It will be interesting to see how Lin plays with Amare and especially Carmelo. We know from Phoenix that Amare is perfectly happy running the pick-and-roll with a good point guard. 'Melo prefers to handle the ball more, so there could be conflict there.

achompas2• 14 years ago

So what if he hasn't played against an elite defensive team. That is irrelevant to determine whether or not he will succeed.

I think the bigger concern is that our small data sample on Lin's performance is significantly biased in that he has played teams with poor defense at the 1 & 2 (guard positions). Derek Fisher is no defensive All-Star.

I can't verify this, though--haven't done sabremetric research in a while. Doesn't Basketball Prospectus have a section ranking guards on their defensive play?

If the Knicks elite players can get their act together, then Lin only needs to contribute positively in order to maintain a strong career.

This is a non-trivial problem. Conditional on being the offense's #1 option, Lin has played well. How will that change when Melo and Amare return, and he has to set them up? When those guys are healthy, Lin is a #3 option at best (maybe lower, as he has no outside jumper).

kevinkemp2• 14 years ago

By most statistical measures, the Lakers are an elite defensive team. They allow only 0.458 efg% and 101 points per 100 possessions. I'm not exactly sure where that rates overall in the league, but I'd guess they are both in the top 15% or so.

weixiyen3• 14 years ago

Lakers are a top 10 defensive team (Bynum and Gasol should have not allowed 38 pts). Kobe has made former all defensive team Lin did a respectable job when Kobe defended him. Lin is probably only going to have trouble vs Westbrook, Wade, Rose, Rondo, and Paul, but at the same time, he is more than good enough to be an NBA starting PG right now.

We have to keep in mind he is doing this well despite the odds stacked against him.

- No jump shooters / scorers in the starting 5. - No practice. - A tremendous amount of expectation and pressure both nationally and internationally.

Dribbling with his left hand and making 3s will come. Derrick Rose took a couple years to get it down in terms of treys. It's a matter of effort, and by all accounts, Lin is a hard worker.

I would be completely shocked if he did not remain a starting PG in the NBA. His effect should only grow as Melo and Amare return.

ecounysis• 14 years ago

How many false positives has this statistician had over their career?

mathattack• 14 years ago

The original post suggests he will be a lottery pick, perhaps first overall. Whoops. The writer caught his being undervalued but overestimated the math skills of basketball GMs.

It's hard to avoid the Linsanity now.

BeeLee• 14 years ago

Great find, GBond. I found it an interesting read. Thanks!

achompas2• 14 years ago

I'm learning/reviewing MCMC methods now for work and...how about a MCMC algorithm that takes in basketball box scores and attempts to generate estimates of each player's ability?

You'd probably have to deal with too many parameters (one for each player in the league)...or maybe not?

Pardon the vagueness, I'm only suggesting this as a theoretical exercise.

EDIT: well, that didn't take long. http://www-stat.wharton.upenn.edu/~zhangk/2010%20Scoring%20a...

stevengg• 14 years ago

here is a good article about how players leverage stats to force the other team into low percentage shots and plays http://www.nytimes.com/2009/02/15/magazine/15Battier-t.html?...

A "Moneyball" statician predicted Jeremy Lin's success 2 years ago

Related Stories