Statistical Analysis. Humor. Knicks.

Sunday, November 23, 2014

Stats & The Straight Dope

If there is anything I enjoy most, it’s setting people straight when they’ve been misinformed. So let’s remove any doubt from the following facts:

* Man Walked on the Moon
* Dinosaurs Walked the Earth (the first two are for Carl Everett)
* Sylvia Browne has no special powers (unless you think convincing people you have special powers is a special power)
* Billy Beane did not write Moneyball
* Eventually there will be a Nuns Gone Wild (link rated PG)

But what about per minute stats in the NBA? What can they tell us about a player? Doing a quick search on the net reveals some diverse opinions.

NBAmaster:
But more importantly, per minute stats are a very bad way of assessing a players ability… Per minute stats have made players like Fizer, Lee Nailon, Tskitivilli, R.White and many more look like the could put up MVP numbers if we converted their stats to 48 mpg. What you need to ask yourself is if those teams really have such an awesome player WHY ISN’T HE GETTING MORE MINUTES? The answer is because he isn’t that good and his limited PT and small sample, usually in garbage time, makes him look better than he is…

Kevin Pelton:
NBA statistical analyst John Hollinger wrote in this year’s edition of his Pro Basketball Forecast series, “It’s a pretty simple concept, but one that has largely escaped most NBA front offices: The idea that what a player does on a per-minute basis is far more important than his per-game stats.”

n:
per minute stats def(inately) don’t stay level with changes in minutes…there are guys whose stats per minute would go down with moe minutes. there are also guys whose numbers per minute go up with moe minutes…though in general it’s still a useful measurement.

And two more from the same thread:
S:
those per 48 minute stats are ridiculous and pretty meaningless. I’ve never seen anyone use those except with (Oster)Tag.

Stockton2Malone:
I don’t think that proves much at all, per 48 minute stats are meaningless.

According to the general public, per minute stats are bad way of assessing a player’s ability, but are more important than per-game stats. They are a useful measurement that changes with a player’s minutes, and are ridiculous and meaningless. Hmmmm, you’d probably get closer to consensus asking one of those riddles that has no real answer like “which ice cream flavor is the tastiest?” or “how do you determine a college football champion without a playoff system?”

Some of these opinions on per minute stats are a bit surprising considering that a study was published on the topic more than 3 years ago. In the 2002 Pro Basketball Prospectus John Hollinger asked and answered the question “Do players do better with more minutes?” For every Washington player, Hollinger looked at each game and separated the stats on whether or not he played more than 15 minutes. He found that when players played more than 15 minutes, they performed significantly better than when they played less. To check his work, he used a control group of 10 random players, and each one of those improved significantly as well.

The knock on Hollinger’s study is the small sample size, containing less than 25 guys from only one season. Enter Justin Kubatko, the site administrator of the NBA’s best historical stat page www.basketball-reference.com. Earlier this week Justin decided to re-examine the theory using a bigger sample size. Taking players from 1978-2004, he identified 465 that played at least a half season and saw a 50% increase in minutes the year after. Three out of four players saw an increase in their numbers as they gained more minutes, although the average increase was small (+1.5 PER).

Two independent studies have shown that NBA players get better when they get more minutes. A conservative interpretation is that per-minute numbers are universal regardless of playing time. So if a player averages 18 points per 40 minutes, he’ll do about that regardless of how many minutes he plays. A more liberal summary would say that underused players will see an improvement in their per-minute numbers if given more court time. A player that only averages 20 minutes a game is likely to be a little bit better if given 35. So the straight dope is per minute stats are a fantastic way to evaluate NBA players. And dinosaurs existed.