August 01 2013 09:39AM
In my previous work I was working on predictions in hockey, at the micro level of a single game, to determine who will win and who will lose. I was using Machine Learning techniques (or algorithmic modeling) and one thing I've noticed from my work, and from reading papers on other peoples material, is that for every sport there seems to be a prediction limit (that is different for every sport). This is what I want to explore; how much of the results that we see are based on luck, and is there a theoretical prediction limit in the NHL?
In this post I will be focusing on the first question, what part of the standings is made up by luck?
July 31 2013 10:44PM
This is the third in a series of articles looking at the history of the NHL Entry Draft from 1979 to 2008. I have tabulated every pick made by every team during that time, selecting out the players who managed 200+ NHL games as draft successes. The initial look is a simple study wherein I credit a team with finding an NHL player, regardless of their draft position or impact on the NHL. The notable weaknesses of this approach are that it evens the playing field between the 3rd line journeyman winger and the franchise defenseman.
July 31 2013 11:46AM
Photo by Bri Weldon via Wikimedia Commons
It's early, but the 2014 NHL Draft is just 11 months away! We don't have much data on the top players yet, and most of the relevant bits seem to come from the Ivan Hlinka Tournament. One thing we do know is that the names involved in the early part of the draft in June are some of the best we've had in a long time: Willie, Leon, Roland, Ivan, Joshua Ho-Sang, Kaspar, Oskar, Sonny, and Arkhip. Toss in Rihards Bukarts for good measure and it's a great group of monikers.
The sources for the consensus list are Future Considerations, ISS, Corey Pronman of Hockey Prospectus. Their rankings are weight by their accuracy in ranking previous drafts: Future Considerations' rankings carry the most weight as they were the most accurate prognosticator in the group.
July 24 2013 12:57PM
In my first look at the origins of NHL draft picks, I noted the drop in selections made from Eastern Europe:
In 2003 and 2004, leagues in Belarus, The Czech Republic, Latvia, Poland, Russia, and Slovakia accounted for 19% of all picks. In 2011 and 2012 those same leagues accounted for just 5% and 4% of all picks. In fact, since 2007, those leagues haven't combined for more than 5% of all selections.
In 2013, it didn't get any better. Leagues in those six countries produces eight draft choices (all from Russian leagues), for 4.3% of the draft.
July 23 2013 10:30AM
By: Patrick D. (SnarkSD) of Fear the Fin
When it comes to statistical analysis the population of interest is everything. Outcomes only apply to the population in the study. Furthermore, any manipulation of the population adds bias to the study. Sometimes this is obvious, but other times it might hide behind a curtain which isn’t obvious, even if we apply tests of statistical significance. That is why methodology is important. In an effort not to bore you, let’s first discuss the more pertinent issue; selection bias, and return to methodology in the end of the article.