Adi Wyner

@adiwyner

Professor of Statistics and Data Science. Co-Faculty director of Wharton Sports Analytics and Business Initiative. co-host of Wharton Moneyball.

1 986Followers

305Following

927Posts total

20.7KViews on collected posts

Against accounts of the same size

12 posts from the last 90 days, next to the under 10K follower range. below its peers on both reach and engagement.

Median views552this account4 686median for under 10K

Reach, %27.77%this account307.95%median for under 10K

Engagement, %0.62%this account1.14%median for under 10K

Metric	This account	Median for under 10K	Ratio
Median views per post	552	4 686	0.12×
Reach (views ÷ followers)	27.77%	3.1× audience	0.09×
Engagement rate	0.62%	1.14%	0.55×

Others in this range → Compare with another account → How these benchmarks are built →

Growth & engagement

How the posts we collected actually performed: views and reaction rate post by post, what the audience did with them, and where the follower count goes.

Views per post

14.5K3 Sep

664

586

782

535

552

497

521

551

495

561

390

Last 12 collected posts, oldest on the left. The scale is logarithmic: one post can outrun the rest a hundred times over.

Engagement rate per post

0.54%3 Sep

0.60%

0.68%

0.64%

0.56%

0.54%

0.60%

0.77%

0.91%

0.61%

1.25%

0.77%

Reactions — likes, reposts, replies and quotes — divided by views. Median for under 10K accounts is 1.14%.

What the audience does

Likes63.2%91 in total

Reposts8.3%12 in total

Replies11.8%17 in total

Quotes2.1%3 in total

Bookmarks14.6%21 in total

Share of every reaction we collected for this account. Replies mean argument, reposts mean endorsement, bookmarks mean the post was worth keeping.

The follower curve appears once this account has two daily snapshots — we take one a day, and this one is on its first.

Latest posts

@adiwyner @tejfbanalytics @RyanPaganetti The data doesn’t explain their intentions it only explains whether it was effective if indeed they did it intentionally 390 views · 2 likes · 0 reposts · 1 replies 03 Sep 2026 11/11 Credit to @AlexPrejean, whose analysis of the Patriots’ kicking gap helped frame this thread. We add attempt-level expectations, home-road comparisons, clustered tests and FDR control: https://t.co/8SbxNzFroi 561 views · 4 likes · 0 reposts · 3 replies 03 Sep 2026 9/11 Blocking: NE opponents had 3.86% of attempts blocked versus 2.15% elsewhere (unadjusted p=.010), accounting for roughly one-third of the missing makes. Remove every block and opponents still finish 4.07 points below expectation. 495 views · 2 likes · 0 reposts · 1 replies 03 Sep 2026 10/11 Verdict: the data show an unusual NE opponent-FG effect—not compelling evidence of a home-only dirty trick. Blocking, weather, kicker mix and special-teams factors? Paganetti’s finding is fun to ponder, but could have happened without the video. 551 views · 3 likes · 0 reposts · 2 replies 03 Sep 2026 The home field effect was larger: −6.46 points at home versus −3.41 on the road. Statistically, no: the home-road difference has p=.38. The data cannot isolate a special Gillette-only mechanism with strong evidence. 7/11 521 views · 3 likes · 0 reposts · 1 replies 03 Sep 2026 8/11 Yet, across all venues, NE opponents went 398-for-518: 76.8% versus 81.8% expected—a −4.94-point gap and 25.6 fewer makes. Clustered p=.0012; 32-team FDR q=.0386. NE was the only FDR-significant negative effect. 497 views · 2 likes · 0 reposts · 1 replies 03 Sep 2026 5/11 At home, NE opponents went 196-for-260: 75.4% versus 81.8% expected. The −6.46-point residual was the largest home-opponent suppression among 32 teams. Clustered p=.0016—but after two-sided BH-FDR control, q=.0526: borderline. 552 views · 2 likes · 0 reposts · 1 replies 03 Sep 2026 On the road, home kickers facing NE went 202-for-258: 78.3% versus 81.7% expected. The −3.41-point residual was also the league’s lowest, but it was not significant: clustered p=.139 and FDR q=.701. 6/11 535 views · 2 likes · 0 reposts · 1 replies 03 Sep 2026 2/11 Paganetti reports that Gillette’s video board showed a reverse view with offset yellow uprights during opponent kicks. That's a testable prediction: NE’s suppression should be distinctly stronger at home than on the road after adjusting for factors that effect kick. 782 views · 4 likes · 0 reposts · 1 replies 03 Sep 2026 4/11 NE’s kickers were excellent: 533-for-618, or 86.2%, versus 84.5% expected (Vinatieri and Gostkowski !! ). But the overall +1.77-point edge was not huge or significant (clustered p=.22). 586 views · 3 likes · 0 reposts · 1 replies 03 Sep 2026 3/11 I modeled all 18,461 regular-season FG attempts from 2001–19. Each kick’s expected probability accounts for distance, indoor/outdoor status, their interaction, and season. I then tested team effects with standard errors clustered by game. 664 views · 3 likes · 0 reposts · 1 replies 03 Sep 2026 Did the Patriots use a dirty home-field trick on opposing kickers? @RyanPaganetti’s video-board finding says yes. The data says: not so fast. The home-road difference isn’t significant, blocks explain part, and home-only evidence is borderline 🧵 1/11 https://t.co/M8w6i2uLK4 14.5K views · 61 likes · 12 reposts · 3 replies 03 Sep 2026

Similar accounts