By The NumbersHockey Analytics... the Final Frontier. Explore strange new worlds, to seek out new algorithms, to boldly go where no one has gone before.
Hey guys. I never did more than a couple of university stats courses, so I doubt I can contribute much besides mindless datamining. However, I'm a huge proponent of using statistics in sports (and life in general), so I'm excited for this forum.
I'm especially looking forward to stats either validating or providing evidence against various instances of conventional hockey wisdom.
I have always enjoyed math and sports, so it's fun for me to try to combine the two. I was fascinated by Bill James' Baseball Abstracts, so that's where my interest in this began. I am most interested in how to compare players from different seasons/era and/or at different positions to each other. My applicable educational background is in Economics, including Econometrics (probability & statistics theory, and economic models).
Last edited by Czech Your Math: 07-27-2012 at 06:49 PM.
I'm of the opinion that hockey is too complex a sport to be accurately measured with numbers. It requires the eye test more than any other sport, by a longshot. Every statistic requires at least two or three layers of context to have any true meaning.
Still, I'll be watching this forum like a hawk, because I'd like to be proven wrong.
I'm Dave. I'm a big fan of statistical analysis though more in the lines of projecting prospects forward then necessarily in terms of player analysis. Which is quite a chore... at best. That said, I'm also a big fan of capology and hopefully I can use some of the data here to not just figure out who are the best players at what they do are, but who are the most affordable for what they do and figuring out who's (and what specific areas are) undervalued league wide.
I'm currently a professor of economics (kinda, it's complicated) with a PhD in physics. Most of what I do these days is more data science than anything else.
Some of my work (on baseball) has been presented at the MIT sloan sports analytics conference. This year I'll likely be headed there with some work on hockey.
In general, my opinion is that despite the 'decoupling' issues that hockey faces (because forward lines and defensive parings) it is likely that quantitative analysis will end up being exploited at the NHL level. Having said that, I doubt much of the impact will result from (re) analysis of the currently recorded statistics. I think that optical tracking, like what's coming online in the NBA, is really where hockey analytics are headed.
Anyways, I'll try to be around this forum as my time constraints allow.
Hi! I majored in Math in university with a concentration in stats; then changed tack altogether and now don't use math at all, except to balance family finances. However, I like the idea of advanced statistics and would love to see how rigorous and, indeed, how useful for predictive purposes some of the more modern analytical statistics can be. As I see it, the minimal G/A/Pts/+-/PIM are only scratching the surface, but I'm not yet convinced Corsi et al are all they claim to be. So.... convince me! And hugely stoked at there being a stats nerd forum.
Hi guys, I am going to post here, not sure what I will do or how I can help out time-wise, but I have a few things that interest me and a bit of math knowledge (teach high school math).
I've always like sports and stats, so mixing the two is an interest of mine. Glad to see this new forum.
I was always fascinated by baseball stats as a boy, and reading Bill James as a teenage started me thinking about which stats were important. From there, branched out to hockey with the Hockey Compendium and basketball with Dean Oliver's work. Minored in stats in university.
Main area of interest statistically: Historical stuff (because I like history and because there's a decent sample size )
Pet peeves: Traditional hockey people who bash advanced stats as number-crunching but rely heavily on traditional stats. Hockey analysts who don't understand the underlying assumptions they have made in their studies, don't understand the importance of the context in which their numbers were generated, and overstate their conclusions. (If Dave Berri ever starts analyzing hockey I will probably spend all my hockey stats time picking his work apart.)
Hope to see more data gathering for future hockey analysis. IMO hockey analysis is heavily constrained by available data, and collecting more data is the best way to improve our knowledge of the game. NHL teams are doing this already if they're smart.
I will definitely try to hover around these parts. Though I think advanced statistics in hockey will reach diminishing returns, its still fun to try. I'm a economist in training and capable of statistical programming so in anybody has a database and an idea, I'd love to help out.
Well this forum looks really cool. I'm a big fan of analysis by advanced statistics in sports, and hockey is my favorite sport so... yeah. That's about it.
You might remember me from such boards as the Hawk board, the main board, the BoH, or the baseball board.
What you don't know about me is that I was pretty awesome in math until I started Algebra in 8th grade. Since then, I have been completely worthless, but I look forward to learning and hope I can contribute in discussion at some point without sounding like a complete dumbass.
My username is my real name, and you can find my stuff online. My blog is here, and I wrote for Hockey Prospectus for some time but not really anymore. And my old site is still around. I've done a lot of statistical analysis on modern players and teams, but generally focus on old stuff now, pre-1927.
My name is Brian. I am a working mathematician. While it is not my primary field I have also taught statistics and probability at various levels. I am quite interested in this forum, though I am also very skeptical of the way many of the "advanced statistics" are used in the blogospere.
That said I have seen some interesting stuff from some posters on HF so I am looking forward to see what people have to say.
I'm going into my senior year of college majoring in Math and Computer Science. Id definitely consider myself more of a computer science student, I love programming and algorithms, but have also recently begun really delving into Machine Learning, and, by extension Stats! Id love to poke around here and learn a few things!
Hello all. My math background is modest (limited to the introductory calc and stats classes needed for my B.Sc), but I've always been fascinated by stats and their application in sports. I was especially drawn in by the work Ken Pomeroy, a college hoops stats guru.
I am one of your mods here. I love doing little studies on whatever topic is of interest to me or my all-time draft buddies at the time. When it gets into more heavy stuff I like to let guys like overpass and iain fyffe do the talking.
)
