QB+ is a quarterback projection metric scaled so that 100 always equals an average NFL starter — the same idea as wRC+ in baseball. A QB+ of 120 means the quarterback projects 20% better than the median starter; 80 means 20% worse. Because it's re-scaled each season, you can compare across years.

How the projections work: The system is spiritually descended from Marcel — the elegant baseball forecasting framework that uses recent history, regresses toward the mean based on sample size, and adjusts for age. Rather than manually specifying how much each signal matters, the model learns optimal weights from hundreds of quarterback-seasons of historical data. A Bayesian hierarchical model is used so that QBs with limited track records are appropriately pulled toward the league mean, while established starters are projected primarily from their own history. An empirically derived aging curve adjusts for the expected year-over-year change at each age.

Credible intervals: Click any player name to see their historical trend and an 80% credible interval on their projection — meaning 80% of model-consistent outcomes fall within the shaded range. Quarterbacks with shorter track records get wider intervals (more uncertainty). Established starters get narrower ones.

Three independent efficiency signals serve as inputs:

• ▸ Quarterback efficiency grades from professional film study — the primary signal, capturing execution quality independent of supporting cast
• ▸ Expected Points Added (EPA) per play — a play-level measure of how much a quarterback moves the win-probability needle on each snap
• ▸ Completion Percentage Over Expectation (CPOE) — how often a quarterback completes passes relative to what the coverage and throw difficulty would predict; used as a predictive input that sharpens the forecast

The two primary signals are projected forward and blended into QB+: efficiency grades (weighted 2/3) and EPA/play (weighted 1/3). Each is independently scaled to median-starter = 100 before combining.

What you're looking at: Every row is a pre-season projection — what the model forecast heading into that season, based only on data available beforehand.