All methods
Game Score
ExperimentalA derived construct without out-of-sample validation - read as informed opinion.
What it means
One number for how good a game (or season) was - scoring, chances and play-driving blended.
How it's computed
Published 2016 weights over box-score events; the default model swaps in expected-goals terms.
What's validated - and what's not
The classic formula is verified against its publication, but the xG-model weights are our own and the index itself carries no out-of-sample accuracy claim - read it as a descriptive blend, not a measurement.
Coverage
2007-08 on; play-driving and xG terms need shift data, so fullest from 2010-11.
Provenance
Dom Luszczyszyn’s Game Score (2016), the classic public formula.
The classic weights are verified against the publication; the default xG-model variant uses our own weights and carries no accuracy claim.
Our research ledger - every source we tested, adopted, or rejected →Tiers are a promise, not a style. Reconciled is checked against the official NHL record; Validated is tested on data the model never fit; Experimental is a derived construct without out-of-sample validation - read it as informed opinion. When in doubt we take the lower tier.