Zone entries and the Sloan Sports Analytics Conference
Eric T.
February 20 2013 11:18AM
Image courtesy Shaun Kreider, Kreider Designs
NHL Numbers previously published a couple of articles on zone entry tracking. We first looked at the results in Flyers games from 2011-12, observing that shot differential at 5-on-5 appears to be largely determined by neutral zone play, and that retaining possession as a team enters the offensive zone is particularly important, generating more than twice as much offense as a dump-and-chase play.
We then called for volunteers to join the project and have had a number of people contribute. We have expanded our database to include a full season of data from the Wild, a half-season of data from the Sabres, a half-season of data from the Capitals, and over 100 assorted games from other teams in 2011-12. This has allowed us to further generalize and strengthen our conclusions for a paper that will be presented at the MIT Sloan Sports Analytics Conference.
How goalies age, and the survivorship bias problem
Eric T.
December 06 2012 02:10PM
Older goalies can still get the job done, but sometimes they need to sit down and rest for a bit.
Photo by rubyswoon via Flickr
This morning, Steve Burtch published a study arguing that goalies do not show any appreciable decline with age. The key plot was this one, in which the x-axis is the goalie's age and the y-axis is how many standard deviations above or below league average he was (for goalies with at least 30 games played):
It's clearly true that the observed performance of old goalies isn't appreciably worse than the observed performance of young goalies. The problem is that word "observed" -- we don't get to observe the performance of all goalies at all ages. JaredL previously looked at this issue and showed how few goalies continue to play heavy minutes into their late 30's. This creates what is called a survivorship bias.
Reference library: Variance and regression
Eric T.
November 14 2012 04:50PM
This article is part of the NHL Numbers reference library, which seeks to collect articles from around the web that have contributed to our understanding of the game.
This page is devoted to articles that look at the role of variance and regression in hockey. This will include looking at how much variance a given statistic has and whether it reflects a true talent, how actual performances compare to random chance models, etc.
We need your help to keep the library complete and up to date -- contact me on Twitter (@BSH_EricT) or via email (bsh.erict -at- gmail) with suggestions of articles you think we should consider adding.
Return to the library main index.
Older players and the grind of a long season
Eric T.
November 13 2012 02:31PM
By the end of the year, Jagr was so tired he sometimes sat down in the middle of a shift
Photo by Michael Miller
I've often heard it suggested that players wear down over the course of a season.
When I wrote about whether players elevate their game in the playoffs, multiple people in the comments argued that players can and should conserve energy during the regular season. It's a particularly common suggestion for older players, who are presumed to be more prone to fatigue. Guys like Jaromir Jagr and Teemu Selanne hate taking days off, but players and coaches are so convinced that they will wear out that they insist on it.
I'm not a physiology expert by any means, so I'm not qualified to make direct assessments of whether older players will suffer more cumulative fatigue than younger players would. However, I am capable of looking at whether such fatigue is born out in the stats.
Putting error bars on NHL equivalencies
Eric T.
November 09 2012 07:40AM
Seguin tripled his point total without even changing leagues. Forecasting is hard.
Photo by Dan4th Nicholas
After I posted the prospects wing of our reference library, I got a couple of interesting replies on Twitter:
I love what the #fancystats community have done, lots of useful stuff, but confidence in their goalie and prospect analysis a bit too high.
@steffeG @Sens_Army_ @NHLnumbers not in that library are any columns pointing to the limits of prospect analysis.
I asked both of them to explain further. (I also defended myself -- my Tweets announcing both of those articles made light of how iffy the stats are in those areas, so I think it was clear that I know there are limitations.) The essence of their feedback, as I understood it, was that by not actively discussing the uncertainty, we as a community have implied that we know more than we do.
This strikes me as a fair criticism, at least in part. It seems like half the articles in the goalie section talk about how unpredictable goalies seem to be, so I'm not sure I'd accept the critique there. But it's pretty rare for us to put actual error bars on our projections. For prospects in particular, there have been a lot of articles written where we give league translation factors to two decimal places; I am pretty certain that the authors did not mean to imply that we can project results to within 1%, but we haven't explicitly laid that out for people.
Can we actually estimate the uncertainty on those projections?
