Building an xG model – v. 1.0

In this article I will take a first crack at building an xG model from scratch. As with most things I do, the approach is slightly different from the other public xG models. Background and purpose: Before we get to the actual model building, it’s important to understand what an xG model is… And whatContinue reading Building an xG model – v. 1.0

Talent distribution – Goaltending (Part IV)

This is the 4th article in the talent distribution series. You can find the other articles here: Part 1, Part 2 and Part 3. This piece will focus on goaltending. What is rink bias? You can’t really discuss goaltender statistics without also mentioning rink bias. Very basically, you can say that rink bias is shotContinue reading “Talent distribution – Goaltending (Part IV)”

Goaltenders have no apparent influence on shot misses!

Introduction In this article I basically seek answers to these two questions: Can a goaltender impact shot misses? How does this affect current goaltender metrics? But before we get to that point, we need to answer a wide variety of questions. In this piece I’m solely looking at 5v5 data, and the shot information isContinue reading “Goaltenders have no apparent influence on shot misses!”

Indications that shot location data is flawed – Depends on where games are being played

Abstract The goal in this article is to determine whether xG data is impacted by where the games are being played. Do certain arenas impact the shot location data one way or the other? All data for this article is 5v5 data from Henrik Lundqvist vs. Tuukka Rask A big part of the inspirationContinue reading “Indications that shot location data is flawed – Depends on where games are being played”