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 · 2024

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
182
targets to trust the number
shrunkrawthe shrink90% CI
65%70%75%80%TE avg1George KittleSF · 9475.9%2Pat FreiermuthPIT · 7875.6%3Jonnu SmithMIA · 11174.9%4Mark AndrewsBAL · 6974.3%5Drew SampleCIN · 2274.3%6Erick AllCIN · 2274.3%7Noah GrayKC · 4974.3%8Mike GesickiCIN · 8374.2%9Dallas GoedertPHI · 5274.2%10Cole KmetCHI · 5974.1%11Nate AdkinsDEN · 1573.9%12Will DisslyLAC · 6473.8%13Trey McBrideARI · 14773.7%14Elijah HigginsARI · 2473.6%15Nick VannettTEN · 2073.5%16Lucas KrullDEN · 2373.4%17AJ BarnerSEA · 3873.4%18Stone SmarttLAC · 1973.4%19Grant CalcaterraPHI · 3073.4%20Austin HooperNE · 5973.3%21Daniel BellingerNYG · 1773.1%22Ja'Tavion SandersCAR · 4373.1%23Josh OliverMIN · 2873.1%24Tanner HudsonCIN · 2473.1%25Brock WrightDET · 1673.0%26Brenton StrangeJAX · 5373.0%27Noah FantSEA · 6473.0%28Eric SaubertSF · 1472.7%29Luke SchoonmakerDAL · 3672.7%30Darnell WashingtonPIT · 2572.7%31Payne DurhamTB · 1472.7%

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 · 2024 · full board

Catch rate leaderboard for the 2024 NFL season, shrunk by empirical Bayes with 90% credible intervals, ranked by the shrunk estimate.
#PlayerTeamPostargetsRawShrunk90% interval
1George Kittle◦ provisionalSFTE9483.0%75.9%71.6%80.0%
2Pat Freiermuth◦ provisionalPITTE7883.3%75.6%71.1%79.9%
3Jonnu Smith◦ provisionalMIATE11179.3%74.9%70.7%79.0%
4Mark Andrews◦ provisionalBALTE6979.7%74.3%69.7%78.7%
5Drew Sample◦ provisionalCINTE2290.9%74.3%69.1%79.2%
6Erick All◦ provisionalCINTE2290.9%74.3%69.1%79.2%
7Noah Gray◦ provisionalKCTE4981.6%74.3%69.4%78.9%
8Mike Gesicki◦ provisionalCINTE8378.3%74.2%69.7%78.5%
9Dallas Goedert◦ provisionalPHITE5280.8%74.2%69.3%78.7%
10Cole Kmet◦ provisionalCHITE5979.7%74.1%69.3%78.6%
11Nate Adkins◦ provisionalDENTE1593.3%73.9%68.6%78.9%
12Will Dissly◦ provisionalLACTE6478.1%73.8%69.1%78.3%
13Trey McBride◦ provisionalARITE14775.5%73.7%69.7%77.6%
14Elijah Higgins◦ provisionalARITE2483.3%73.6%68.4%78.5%
15Nick Vannett◦ provisionalTENTE2085.0%73.5%68.3%78.5%
16Lucas Krull◦ provisionalDENTE2382.6%73.4%68.3%78.4%
17AJ Barner◦ provisionalSEATE3879.0%73.4%68.4%78.2%
18Stone Smartt◦ provisionalLACTE1984.2%73.4%68.2%78.4%
19Grant Calcaterra◦ provisionalPHITE3080.0%73.4%68.3%78.2%
20Austin Hooper◦ provisionalNETE5976.3%73.3%68.5%77.8%
21Daniel Bellinger◦ provisionalNYGTE1782.3%73.1%67.8%78.2%
22Ja'Tavion Sanders◦ provisionalCARTE4376.7%73.1%68.2%77.9%
23Josh Oliver◦ provisionalMINTE2878.6%73.1%68.0%78.0%
24Tanner Hudson◦ provisionalCINTE2479.2%73.1%67.9%78.0%
25Brock Wright◦ provisionalDETTE1681.3%73.0%67.7%78.0%
26Brenton Strange◦ provisionalJAXTE5375.5%73.0%68.1%77.6%
27Noah Fant◦ provisionalSEATE6475.0%73.0%68.2%77.5%
28Eric Saubert◦ provisionalSFTE1478.6%72.7%67.4%77.8%
29Luke Schoonmaker◦ provisionalDALTE3675.0%72.7%67.7%77.6%
30Darnell Washington◦ provisionalPITTE2576.0%72.7%67.5%77.7%
31Payne Durham◦ provisionalTBTE1478.6%72.7%67.4%77.8%
32Brock Bowers◦ provisionalLVTE15373.2%72.7%68.6%76.6%
33Foster Moreau◦ provisionalNOTE4374.4%72.7%67.7%77.5%
34Juwan Johnson◦ provisionalNOTE6873.5%72.6%67.9%77.1%
35Taysom Hill◦ provisionalNOTE3174.2%72.6%67.4%77.5%
36Chig Okonkwo◦ provisionalTENTE7173.2%72.5%67.8%77.0%
37Josh Whyle◦ provisionalTENTE3873.7%72.5%67.5%77.3%
38Harrison Bryant◦ provisionalLVTE1275.0%72.5%67.0%77.6%
39Travis Kelce◦ provisionalKCTE13472.4%72.3%68.1%76.4%
40Isaiah Likely◦ provisionalBALTE5872.4%72.3%67.5%77.0%
41Sam LaPorta◦ provisionalDETTE8372.3%72.3%67.7%76.7%
42Tommy Tremble◦ provisionalCARTE3271.9%72.2%67.1%77.1%
43Luke Farrell◦ provisionalJAXTE1770.6%72.1%66.8%77.2%
44Johnny Mundt◦ provisionalMINTE2770.4%72.0%66.8%77.0%
45Tyler Higbee◦ provisionalLATE1266.7%71.9%66.5%77.1%
46Pharaoh Brown◦ provisionalSEATE1266.7%71.9%66.5%77.1%
47Cade Stover◦ provisionalHOUTE2268.2%71.8%66.5%76.9%
48Zach Ertz◦ provisionalWASTE9371.0%71.8%67.3%76.2%
49Tucker Kraft◦ provisionalGBTE7170.4%71.8%67.0%76.3%
50Andrew Ogletree◦ provisionalINDTE1464.3%71.7%66.3%76.9%
51Brevyn Spann-Ford◦ provisionalDALTE1464.3%71.7%66.3%76.9%
52Evan Engram◦ provisionalJAXTE6770.2%71.7%66.9%76.3%
53Tyler Conklin◦ provisionalNYJTE7369.9%71.6%66.8%76.1%
54Gerald Everett◦ provisionalCHITE1361.5%71.6%66.1%76.7%
55Hayden Hurst◦ provisionalLACTE1361.5%71.6%66.1%76.7%
56John Bates◦ provisionalWASTE1361.5%71.6%66.1%76.7%
57Jordan Akins◦ provisionalCLETE5869.0%71.5%66.6%76.2%
58Dawson Knox◦ provisionalBUFTE3366.7%71.4%66.3%76.4%
59Charlie Woerner◦ provisionalATLTE1258.3%71.4%66.0%76.6%
60Theo Johnson◦ provisionalNYGTE4367.4%71.4%66.3%76.2%
61Michael Mayer◦ provisionalLVTE3265.6%71.3%66.1%76.2%
62Jeremy Ruckert◦ provisionalNYJTE2864.3%71.2%66.0%76.2%
63Jake Ferguson◦ provisionalDALTE8668.6%71.1%66.5%75.5%
64Julian Hill◦ provisionalMIATE2060.0%71.1%65.7%76.2%
65Adam Trautman◦ provisionalDENTE2259.1%70.9%65.5%76.0%
66Cade Otton◦ provisionalTBTE8767.8%70.8%66.2%75.3%
67Hunter Henry◦ provisionalNETE9768.0%70.8%66.3%75.2%
68T.J. Hockenson◦ provisionalMINTE6266.1%70.7%65.8%75.4%
69Durham Smythe◦ provisionalMIATE1752.9%70.6%65.2%75.8%
70Davis Allen◦ provisionalLATE1346.2%70.5%65.1%75.8%
71Greg Dulcich◦ provisionalNYGTE1241.7%70.4%64.9%75.6%
72Mo Alie-Cox◦ provisionalINDTE2352.2%70.0%64.7%75.2%
73Colby Parkinson◦ provisionalLATE4961.2%69.9%64.9%74.8%
74Kyle Pitts◦ provisionalATLTE7463.5%69.7%64.9%74.4%
75David Njoku◦ provisionalCLETE9964.6%69.6%65.0%74.0%
76Dalton Schultz◦ provisionalHOUTE8562.4%69.1%64.4%73.7%
77Kylen Granson◦ provisionalINDTE3145.2%68.3%63.0%73.5%
78Dalton Kincaid◦ provisionalBUFTE7558.7%68.3%63.5%73.0%

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).