Week 1 Bayesian Quarterback Rankings

Adjusted Quarterback Efficiency (AQE) now part of the most well calibrated projections

The numbers show Josh Allen as the clear No. 2 quarterback in the NFL, no matter what the haters say

The big, fundamental change to the rankings this season is integrating my Adjusted Quarterback Efficiency (AQE) numbers that we can calculate over the last two seasons. This produces rankings that align more closely to what the typical football observer or data-based analysts would assign based on a combination of observation and statistics.

You can find all the previous weekly editions of the Bayesian Quarterback Rankings here, and the backlog for Adjusted Quarterback Efficiency is here.

COMPARING GRADES AND EFFICIENCY

PFF grades aren’t part of the analysis, but I find it helpful to make not of how they align with EPA per play, as many contextual elements of quarterback play (drops, interception-worthy throws, easier throws that become big gains, etc) are part of the grading methodology, but aren’t accounted for in EPA. At the same time, I think EPA does a vastly superior job of weighing what is and isn’t important in points-based results.

Looking back over the aggregate numbers for PFF grading and EPA efficiency for a number of current NFL quarterbacks, you see the strong correlation between the measures, with some outliers with both higher and lower efficiencies than expected.

Brock Purdy is the big outlier with EPA efficiency well above the crowd, yet a PFF grade that ranks on the edge of the top-5. As you’ll see below, his Bayesian rankings fall closer to the PFF grade after accounting for a discount in his adjusted efficiency.

On the flip side, someone like Daniel Jones has been better according to PFF grading than his EPA efficiency, but the adjusted numbers don’t give him much of a boost. The same goes for others with the same grade-EPA relationship, including Joe Burrow, C.J. Stroud, Russell Wilson and Geno Smith.

Eliminating the young (or bad) quarterbacks at the bottom-left of the plot, we can focus more on the recent results for the majority of starters.

What you find is a large grouping of quarterbacks in the 0.1-0.2 EPA per play and 80-85 PFF offensive grade ranges. This is a good illustration of how closely many quarterbacks are grouped, not only on the plot but in the rankings.

Below shows how the quarterbacks’ adjusted efficiency has compared to actual over the last two years.

Purdy gets an enormous discount of over 0.1 EPA per play, along with big declines for Jordan Love, Tua Tagovailoa, Jared Goff and C.J. Stroud. Remember those numbers when certain quarterbacks have Bayesian rankings that differ significantly from their recent performance.

WEEK 1 PROJECTED ADJUSTED EFFICIENCY

These results are the ranking for the go-forward projections of adjusted quarterback efficiency starting in Week 1. I also included the EPA per play rankings for each quarterback over the last five seasons (minimum 250 dropbacks) so you can see the evidence going into the projections. The numbers for 2022 and 2023 at the “actual” EPA per play rankings, whereas the projections are fed the adjusted numbers illustrated above.

Older data is decayed over time, so the 2023 and 2022 EPA per play data matters more than those from pre-2020. That said, older data can’t be fully discounted, or else you miss bounce-back performers of great quarterbacks returning to form, like Aaron Rodgers in 2020 and 2021.

For Week 1, I’m excluding the three rookie starters (Caleb Williams, Jayden Daniels and Bo Nix). They will be added next week with the actual NFL evidence from Week 1 of the season. The baseline expectation for a quarterback drafted in the top-half of the first round is to rank in the bottom-10 for EPA efficiency, with a No. 1 overall pick a bit higher at around 20th.

“Percentile” is the mean (“best guess”) projection as a percentile of historical franchise quarterback results (min 2K career dropbacks).