Archive for the 'Statistical +/-' Category

With a 2-0 lead in their conference semifinal series, this year's Suns team is currently looking like a good bet to defeat their hated archrivals, the San Antonio Spurs, and make the Western Conference Finals. The Suns have never advanced past the Conference Finals in the Nash era, and this year's likely WCF opponents have been a tough nut for Phoenix to crack, but it looks like the 2010 season is shaping up to be as good an opportunity as any in recent memory for Phoenix to make the Finals.

If you had told me a few years ago that we'd be saying this in May of 2010, after Mike D'Antoni departed and Steve Kerr shifted the franchise's direction with the acquisition of Shaquille O'Neal for Shawn Marion, I would have said you were crazy. Even now, this Suns team doesn't "feel" as great as the team that went deep in the 2005/06/07 playoffs, but here they are, with a chance to do something that the earlier incarnations of the Nash Suns never did. So how do these Suns stack up to Phoenix's past playoff teams?

Read the rest of this entry »

Watching Boston destroy Cleveland in the second half of last night's game, on Cleveland's home court, made me think about surprising playoff outcomes. Going into a game between Boston and Cleveland at Quicken Loans Arena, you would expect the Cavs to win by at least ~3.3 points even if you knew nothing about the two teams, since that's the average margin by which the home team wins any given game. And if you did know about the relative quality of the two teams -- Boston won 61% of its regular-season games, Cleveland won 74% -- you would expect Cleveland to win by even more. An example: using SRS, you might expect the Cavs to win by roughly 6 points (6.2 - 3.4 + 3.3 = 6.1). And, not coincidentally, the betting line on last night's game was Cleveland -6. But instead, Boston won by 18, a difference of 24 vs. what we would have expected going into the game.

Read the rest of this entry »

As if everyone isn't already tired of this debate (one which will never be satisfactorily settled, I'm sure), here's a final note on who contributed the most to the 1995 Rockets' offense during the playoffs, Hakeem Olajuwon (mega-high usage, average efficiency) or Clyde Drexler (mid-to-high usage, mega-high efficiency)...

My last post attempted to create a simple model of team offensive efficiency using Dean Oliver's Offensive Rating, Possession %, and what Dean called "Skill Curves", or the relationship between changes in individual usage and efficiency rates. In general, both Oliver and Eli Witus found a quantifiable inverse relationship between increases in usage and predicted offensive efficiency -- in other words, there's diminishing returns to increasing your usage, and as you add more usage you become less and less efficient (which only makes sense to anyone who's ever played basketball).

Read the rest of this entry »

Whenever Hall of Fame arguments come up, especially in baseball, I have a tendency to tune out from the sheer tediousness of the typical debate. On one side, there's always an arrogant guy who saw many of Player X's games and "knows" he's a Hall of Famer, so he cites other, lesser players who are already in the Hall (as though that were somehow evidence Player X should be in), brings up a couple of memorable career moments, and generally fudges on borderline issues to make the player seem better than he actually was. On the opposing side, another equally narcissistic guy splits hairs about the "magic numbers" Player X failed to reach, denigrates his career because A) if he won titles, he didn't have enough individual honors; or B) if he had a lot of individual honors, he didn't win enough titles. Throw in a few unsubstantiated jabs at Player X's character and/or manhood, and then start the whole process over again -- how fun.

Read the rest of this entry »

Continuing our series on huge playoff upsets, I've taken the methodology I laid out on Friday and applied it to every playoff series from 1991-2009 to determine the probability of each team winning, given the distribution of minutes for their players in the series. This is accomplished by finding weighted averages of the team's players' and opponents' seasonal SRS-SPM scores (see Part I for an explanation), and plugging them into the following equation to produce a single-game expected winning %:

xWP = 1 / (1 + exp(0.622 - 0.168(tm_srs) + 0.168(opp_srs) - 1.244(homecourt)))

Again, where homecourt = 1 if the team is at home and 0 if they're on the road. Armed with these single-game probabilities, all that's left is to use them to calculate the odds of winning a series of a given length with a given # of home games. This of course means you need to calculate not only the probability of each series outcome, but also the probability that the series ends in each specific # of games (for instance, winning a series in four games would require 4 consecutive wins -- WWWW -- while you could win in five games four different ways -- WWWLW, WWLWW, WLWWW, or LWWWW).

Read the rest of this entry »

Back in the spring, I used Statistical Plus/Minus to predict individual playoff series outcomes (and to pretty decent effect, too -- I mean, yes, it did miss on Cleveland-Orlando, but then again so did just about everyone, including the bigwigs at Nike). Anyway, today I'm going to use a similar method to look back on every playoff game from 1991-2009 and see which games ended in the most unlikely outcomes.

Read the rest of this entry »

Last week, we took a very preliminary look at what our Statistical Plus/Minus projection system saw in the cards for the 2009-10 NBA Season. To project minutes played, we used a very simplistic regression equation that took a weighted average of a player's minutes over the past three seasons and regressed it heavily to the mean. Of course, this is a very rough way to estimate what a player's minutes will be next season; in fact, the standard error of the playing time regression (done on all players from 1978-2009) was 674.8, meaning that the prediction was likely to be off by a significant amount in either direction, too high or too low. As you might guess, this could severely impact the accuracy of the projected standings.

Read the rest of this entry »

Since everyone seems to be jumping on the projection bandwagon right now, here are the preliminary projected standings for 2010 (I'll explain the process at the bottom):

Read the rest of this entry »

Click here for the results from Round 3.

Read the rest of this entry »

Click here for the results from Round 2.

Read the rest of this entry »