Do tell, how is game score measured.
I couldn't find a site. But I will quote few pieces. It would be too long if I quoted the whole thing.
"How the model works
It’s mostly outlined here in this
FAQ posted before our 2017-18 projections, but basically it’s built at the player level using
Game Score – a stat I adapted from basketball a few years ago. Working at the player level rather than the team level is one way that my model differs from others that are scaled via team performance only. It offers some challenges in terms of allocating proper credit, but has the advantage of being able to instantly factor for injuries and trades in ways a team-level model cannot.
Game Score is a linear weight model with the weights for each stat within it being derived according to the frequency of goals occurring from them and are as such:
Goals: 0.75
Primary Assists: 0.7
Secondary Assists: 0.55
Shots: 0.075
Blocks: 0.05
Penalty Differential: 0.15
Faceoff Differential: 0.01
5-on-5 Corsi Differential: 0.05
5-on-5 Goal Differential: 0.15
It uses data from each player’s last three seasons, with each component weighted by recency and regressed to the mean individually. That means that the weight for each prior season is different for goals than it is for shots or blocks (and different for forwards and defencemen), as is the regression factor. On top of that, there’s an age adjustment (using methods outlined
here) performed at the start of each year that slowly lessens until the end of the season, as well as a small
usage adjustment that factors in a player’s teammates and competition based on 5-on-5 Game Score.
From there, each player has a projection for each component going forward and that’s plugged into the Game Score formula to get a projected Game Score going forward. That’s then transformed into a wins above replacement rate (with replacement level being the 372nd forward and 186th defenceman) to create Game Score Value Added, or GSVA. That value is added up for each team based on the players in their starting lineup, and voila: team strength projections.
So what’s different now then? Glad you asked.
Better accounting for defence (and more emphasis on play-driving)
One of the largest downfalls of my model has always been a bias toward offence. Defence matters and needs to be accounted for better.
The reason for that is simply that there are a lot of offensive box score stats to include in Game Score and just not many defensive ones. It’s worked out fine until now (largely because a lot of the credit just went to the goalie and offence being much easier to predict), but there’s a bit of egg on my face with two of the league’s best defensive teams squaring off in the final. Again, strong offensive teams (Toronto, Chicago) were disproportionately favoured relative to the market over strong defensive teams (St. Louis, Islanders).
To properly account for skater defence all we really have is a player’s shot suppression numbers, so it’s time to ramp those up a bit. I looked at the average player’s Game Score for each team over the last decade per position, separated his individual contributions from his on-ice contributions at both offence and defence and then compared that to the team’s goal differential to see just how much of an increase needed to be made. For forwards, it was by a factor of 2.92, and for defencemen it was 3.83 – so … significantly more important than previously measured. Oops.
There’s one more added wrinkle: increasing the effect of offensive play-driving too. For forwards, things increase slightly by a factor of 1.67, but for defenders it’s much larger at 2.83. That leaves the following weights for expected goals and goals (measured as a combination of relative to average and relative to team):
F xGF: 0.625
F GF: 0.625
F xGA: 1.75
F GA: 0.4375
D xGF: 1.7
D GF: 0.425
D xGA: 2.3
D GA: 0.575
The difference between offensive and defensive play-driving should partially counterbalance the amount of credit players get for individual contributions which skew toward the fun part of the ice. This is especially helpful for defenders who now receive much more credit for where the puck is when they’re on the ice, rather than simply on points scored – a much-needed improvement."
Should give some sort of picture about GS. Now to bed.
