It's been a while since the last post, but that means that actual work has been going on! In April I went to the Vancouver Hockey Analytics Conference and I thought I'd post a video of the talk for all to see.
I know you've been waiting on the edge of your seat for this analysis, asking yourself: how well did ELO do so far? Oh my gosh, I can't wait any longer to see Dave's predictions for the conference championships?
This will be a fun post, though I need to type fast because the 2015 Stanley Cup playoffs officially kicked off last night! In this post I will present Monte Carlo playoff simulations, using team-Elo values heading into the playoffs to make assign game win probabilities.
In this post we determine the degree of bias in plus/minus for players on good teams versus bad, by tracking the performance of players before and after trades. The same analysis shows the Elo statistic to be unbiased with respect to team!
How can we tell that the Elo algorithm is doing a good job of evaluating players? Can we predict who is going to win a game based on the team-Elo?
We'll see what the online NHL data has to say about the value of winning a faceoff.