NFL · Empirical Bayes

True-Talent Leaderboards

A raw single-season rate is a noisy guess at a player’s real ability, and the noise is worst for the smallest samples — so a naïve leaderboard is topped by whoever got lucky in the fewest tries. This one shrinks every rate toward its position-group prior by how much the sample can be trusted, and shows a 90% credible interval instead of a point. Toggle raw vs. shrunk to watch the flukes fall back to the pack.

Catch rate · 2025

Receptions per target, shrunk within position (WR vs TE separately). Depth-of-target confound; catchable-target rate not available here.

Beats raw by
18.3%
lower out-of-sample error
RMSE raw → shrunk
11.1% → 9.1%
odd vs. even weeks
Split-half reliability
0.35
how repeatable the raw stat is
Stabilizes at
2512
targets to trust the number
shrunkrawthe shrink90% CI
71%72%73%74%TE avg1Jake FergusonDAL · 10372.5%2George KittleSF · 6972.5%3Dalton SchultzHOU · 10772.4%4Sam LaPortaDET · 4972.4%5Ja'Tavion SandersCAR · 3472.4%6Noah FantCIN · 4172.4%7Gunnar HelmTEN · 5572.4%8Ian ThomasLV · 1372.4%9T.J. HockensonMIN · 6672.4%10Juwan JohnsonNO · 10272.4%11Adam TrautmanDEN · 2372.4%12Elijah HigginsARI · 3772.4%13Trey McBrideARI · 17072.3%14Dalton KincaidBUF · 5072.3%15AJ BarnerSEA · 6872.3%16Colby ParkinsonLA · 5672.3%17Brenton StrangeJAX · 6072.3%18Austin HooperNE · 2672.3%19Jackson HawesBUF · 1972.3%20Pat FreiermuthPIT · 5472.3%21Kyle PittsATL · 11972.3%22Jeremy RuckertNYJ · 2972.3%23Tanner HudsonCIN · 2472.3%24Greg DulcichMIA · 3472.3%25Luke MusgraveGB · 3172.3%26Ben SinnottWAS · 1372.3%27John FitzPatrickGB · 1572.3%28Brock BowersLV · 8772.3%29Luke FarrellSF · 1472.3%30Isaiah LikelyBAL · 3672.3%31Mitchell EvansCAR · 2572.3%32Josh OliverMIN · 2072.2%33Drew SampleCIN · 2072.2%

Each row is a player: the solid dot is the shrunk estimate, the hollow dot the raw rate, joined by the red pull of regression; the grey bar is the 90% credible interval. A hollow shrunk dot means the sample is below the stabilization line — the number is mostly the position prior. Switch to Raw rank and watch the small-sample names climb.

Catch rate · 2025 · full board

Catch rate leaderboard for the 2025 NFL season, shrunk by empirical Bayes with 90% credible intervals, ranked by the shrunk estimate.
#PlayerTeamPostargetsRawShrunk90% interval
1Jake Ferguson◦ provisionalDALTE10379.6%72.5%71.1%73.9%
2George Kittle◦ provisionalSFTE6982.6%72.5%71.0%73.9%
3Dalton Schultz◦ provisionalHOUTE10776.6%72.4%71.0%73.8%
4Sam LaPorta◦ provisionalDETTE4981.6%72.4%70.9%73.8%
5Ja'Tavion Sanders◦ provisionalCARTE3485.3%72.4%70.9%73.8%
6Noah Fant◦ provisionalCINTE4182.9%72.4%70.9%73.8%
7Gunnar Helm◦ provisionalTENTE5580.0%72.4%70.9%73.8%
8Ian Thomas◦ provisionalLVTE13100.0%72.4%70.9%73.8%
9T.J. Hockenson◦ provisionalMINTE6677.3%72.4%70.9%73.8%
10Juwan Johnson◦ provisionalNOTE10275.5%72.4%70.9%73.8%
11Adam Trautman◦ provisionalDENTE2387.0%72.4%70.9%73.8%
12Elijah Higgins◦ provisionalARITE3781.1%72.4%70.9%73.8%
13Trey McBride◦ provisionalARITE17074.1%72.3%70.9%73.8%
14Dalton Kincaid◦ provisionalBUFTE5078.0%72.3%70.9%73.8%
15AJ Barner◦ provisionalSEATE6876.5%72.3%70.9%73.8%
16Colby Parkinson◦ provisionalLATE5676.8%72.3%70.9%73.8%
17Brenton Strange◦ provisionalJAXTE6076.7%72.3%70.9%73.8%
18Austin Hooper◦ provisionalNETE2680.8%72.3%70.8%73.8%
19Jackson Hawes◦ provisionalBUFTE1984.2%72.3%70.8%73.8%
20Pat Freiermuth◦ provisionalPITTE5475.9%72.3%70.8%73.7%
21Kyle Pitts◦ provisionalATLTE11974.0%72.3%70.9%73.7%
22Jeremy Ruckert◦ provisionalNYJTE2979.3%72.3%70.8%73.8%
23Tanner Hudson◦ provisionalCINTE2479.2%72.3%70.8%73.7%
24Greg Dulcich◦ provisionalMIATE3476.5%72.3%70.8%73.7%
25Luke Musgrave◦ provisionalGBTE3177.4%72.3%70.8%73.7%
26Ben Sinnott◦ provisionalWASTE1384.6%72.3%70.8%73.7%
27John FitzPatrick◦ provisionalGBTE1580.0%72.3%70.8%73.7%
28Brock Bowers◦ provisionalLVTE8773.6%72.3%70.8%73.7%
29Luke Farrell◦ provisionalSFTE1478.6%72.3%70.8%73.7%
30Isaiah Likely◦ provisionalBALTE3675.0%72.3%70.8%73.7%
31Mitchell Evans◦ provisionalCARTE2576.0%72.3%70.8%73.7%
32Dallas Goedert◦ provisionalPHITE8273.2%72.3%70.8%73.7%
33Jake Tonges◦ provisionalSFTE4673.9%72.3%70.8%73.7%
34Josh Oliver◦ provisionalMINTE2075.0%72.2%70.8%73.7%
35Drew Sample◦ provisionalCINTE2075.0%72.2%70.8%73.7%
36Cade Stover◦ provisionalHOUTE1675.0%72.2%70.8%73.7%
37Tommy Tremble◦ provisionalCARTE3773.0%72.2%70.8%73.7%
38Daniel Bellinger◦ provisionalNYGTE2673.1%72.2%70.8%73.7%
39Tucker Kraft◦ provisionalGBTE4472.7%72.2%70.8%73.7%
40Davis Allen◦ provisionalLATE3372.7%72.2%70.8%73.7%
41Dawson Knox◦ provisionalBUFTE5072.0%72.2%70.8%73.7%
42Hunter Long◦ provisionalJAXTE1770.6%72.2%70.7%73.7%
43Grant Calcaterra◦ provisionalPHITE1369.2%72.2%70.7%73.7%
44Cade Otton◦ provisionalTBTE8272.0%72.2%70.8%73.7%
45Julian Hill◦ provisionalMIATE2171.4%72.2%70.7%73.7%
46Brevyn Spann-Ford◦ provisionalDALTE1369.2%72.2%70.7%73.7%
47Taysom Hill◦ provisionalNOTE1668.8%72.2%70.7%73.7%
48Will Dissly◦ provisionalLACTE1668.8%72.2%70.7%73.7%
49John Bates◦ provisionalWASTE1668.8%72.2%70.7%73.7%
50Charlie Kolar◦ provisionalBALTE1566.7%72.2%70.7%73.6%
51Darnell Washington◦ provisionalPITTE4470.5%72.2%70.7%73.6%
52Oronde Gadsden II◦ provisionalLACTE6971.0%72.2%70.7%73.6%
53Tyler Higbee◦ provisionalLATE3669.4%72.2%70.7%73.6%
54Chig Okonkwo◦ provisionalTENTE7970.9%72.2%70.7%73.6%
55Michael Mayer◦ provisionalLVTE5070.0%72.2%70.7%73.6%
56Darren Waller◦ provisionalMIATE3568.6%72.2%70.7%73.6%
57Mo Alie-Cox◦ provisionalINDTE2065.0%72.2%70.7%73.6%
58David Njoku◦ provisionalCLETE4868.8%72.2%70.7%73.6%
59Jonnu Smith◦ provisionalPITTE5569.1%72.2%70.7%73.6%
60Brock Wright◦ provisionalDETTE2263.6%72.2%70.7%73.6%
61Tanner Conner◦ provisionalMIATE1560.0%72.2%70.7%73.6%
62Colston Loveland◦ provisionalCHITE8369.9%72.2%70.7%73.6%
63Zach Ertz◦ provisionalWASTE7368.5%72.1%70.7%73.6%
64Travis Kelce◦ provisionalKCTE10969.7%72.1%70.7%73.6%
65Mark Andrews◦ provisionalBALTE7068.6%72.1%70.7%73.6%
66Luke Schoonmaker◦ provisionalDALTE2360.9%72.1%70.6%73.6%
67Hunter Henry◦ provisionalNETE8769.0%72.1%70.7%73.6%
68Mike Gesicki◦ provisionalCINTE4365.1%72.1%70.6%73.6%
69Mason Taylor◦ provisionalNYJTE6666.7%72.1%70.6%73.5%
70Elijah Arroyo◦ provisionalSEATE2657.7%72.1%70.6%73.5%
71Johnny Mundt◦ provisionalJAXTE1947.4%72.0%70.6%73.5%
72Cole Kmet◦ provisionalCHITE4961.2%72.0%70.5%73.5%
73Evan Engram◦ provisionalDENTE7764.9%72.0%70.5%73.5%
74Harold Fannin Jr.◦ provisionalCLETE10866.7%72.0%70.5%73.4%
75Tyler Warren◦ provisionalINDTE11466.7%72.0%70.5%73.4%
76Noah Gray◦ provisionalKCTE3855.3%72.0%70.5%73.4%
77Terrance Ferguson◦ provisionalLATE2544.0%71.9%70.5%73.4%
78Theo Johnson◦ provisionalNYGTE7460.8%71.9%70.4%73.3%

How the shrinkage works

Two estimators

Rate stats (completion %, success rate, catch rate) use a beta-binomial model: a Beta(α, β) prior fit by marginal likelihood over each position group, then a Beta posterior per player. Per-play averages (EPA, CPOE, yards) use a normal-normal model with DerSimonian–Laird between-player variance. Both pull each player toward their group by exactly how thin their sample is.

Does it help? & the fine print

The trust panel’s numbers come from a leakage-free odd/even-week holdout: fit on odd weeks, predict even-week raw. Shrinkage lowers out-of-sample error for every stat. Priors are fit per season and per position (WR and TE separately), so a TE’s baseline isn’t a skill. Regular season only, 2016–2025. Rushing and receiving efficiency are heavily scheme-driven — read the wide bands as the honesty they are.

Source: nflverse play-by-play. Counted and computed deterministically — never modeled by a language model. Built by build_nfl_leaderboards.py (byte-reproducible).