A stats-driven power ranking

Check out this post on the new version of Rink Stats. I used the win probability metric, which I described here, to calculate the average probability that each team wins each of their games. Then, for each team, I calculate a weighted-average (based on the logged temporal distance) of their win probabilities. In other words, the most recent game gets the highest weight, while game 1 is still in the calculation, but significantly down-weighted.

The result is a new power ranking metric, which is entirely based on in-game statistics. As far as I know (and please correct me if I'm wrong) but it's also the first power ranking (in any sport?) which doesn't just provide the ranks of the teams (1 through 30) but gives a sense of how big the gaps are between teams 1 and 2, 2 and 3, etc. Check out the results below, which are based on every game this season (excluding last night's).

As you can see, not only is Boston the top-ranked team, it's doing significantly better than the other teams in the top 5, mostly because of their dominance during their 12 game win streak. And you can see there's a huge dropoff in teams 25-30.

Win probabilities metric 1.0

Check out this post on the new version of Rink Stats. In the past few years, in-game win probability metrics have become increasingly common in the NFL, MLB, and NBA. Similar analytics for the NHL, however, have lagged behind. In this post I'll present version 1.0 of my NHL win probabilities metric.

So far, the metric is based on home ice advantage, score differential, and penalty time. The model is flexible enough, though, in include other factors like puck possession or (hopefully eventually) players-on-ice.

I'll assume that most people won't be interested in the statistical underpinnings, so I'll leave that for the end of the post and start by presenting some examples of the model applied to a recent games.  Also, I've got some cool ideas of things I can do with this metric, but I'd love to hear any feedback you have. Plus, I'm still trying to think of a catchy name for the stat, so if you have any ideas let me know.

Win probabilities

Check out this post on the new version of Rink Stats. I started working today on a new project. I'm trying to build a dataset that allows somebody to get the probability of a team winning a game, given the current score, time remaining, PP situation, and other variables. So far I've built the score and time remaining into my model, although hopefully in the next few days I'll add PP/SH info.

I also am trying to find a nice looking way to present the results. Below is what I have so far. This is the win probability from the exciting game 6 of the Stanley Cup Finals last year, in which Chicago trailed by a goal with less than 2 minutes left and ended up winning the game in regulation.

I'd love anybody's feedback (via email, Twitter, Facebook, wherever) on where you think I should go with this or how I can make the graphs look nicer.

In a crazy twist, it looks like Extra Skater has rolled out a similar metric today as well. I think mine looks fancier though.

​How The Long-Change OT Could Cut NHL Shootouts By A Third

Check out this post on the new version of Rink Stats. I just wrote my first article for Deadspin. A hot topic in the NHL community this week has been the possibility of tweaking the overtime rules to generate more goals and fewer shootouts. In the article, which is a followup to an article I wrote here a few months back, I look at the potential consequences of one of the proposed rules changes. I find that having the teams switch sides in OT, so that all 5 minutes are played with the long-change could drop the number of shootouts by a third.

A snippet:

"...we should expect that 34.29 percent of the games that go to a shootout under the current rules would instead be resolved by a game-winning goal in overtime (plus/minus 3.45 percent). In other words, if the NHL GMs adopt the proposal to make regular season overtimes use the long change, the number of shootouts in the 1,230 game season would drop from about 166 (13.5 percent of games) to about 109 (8.87 percent)."