If you're planning to be at the SABR Analytics conference, feel free to reach out so we can connect!
26.02.2026 01:35
👍 3
🔁 1
💬 1
📌 0
If you're planning to be at the SABR Analytics conference, feel free to reach out so we can connect!
so far tonight bad bunny has sung more reggaeton songs than the patriots and seahawks combined
Wow, that's a lot more often than I was expecting, especially for something so subjective
I rarely watch football, how common are penalties for unsportsmanlike conduct??
The 0.5.0 version of my {brms} + {tidyverse} translation of McElreath's "Statistical Rethinking" (2nd ed) is up!
solomon.quarto.pub/sr2/
1/3
#rstats
i wanna be sworn into office with this book
I wasn't able to contribute this year, but I'm definitely putting in an order – and I highly recommend that you do the same!
"The result isn’t optimization, it’s about survival"
Really enjoyed working on this piece with @jrodrigues39.bsky.social on how swings age, building off work from @justinochoi.bsky.social. Link to the code behind it below!
www.baseballprospectus.com/news/article...
Hi, BlueSky converts. Probably deserves some updating, but here's a list of baseball analytics nerds if that's up your alley.
go.bsky.app/GZjLuxK
Really enjoyed this article from @benclemens.bsky.social!
Hey, SABR hasn't put both its feet into bluesky yet (I know, a lot of its people have) but this is a good time to remind you that the SABR Analytics Conference Research Awards are open for nominations.
When you have a few minutes, please nominate some of your favorite baseball research from 2025.
The code is all here! The raw data is masked, as that is proprietary @baseballprospectus.com data. But BP subscribers should be able to access the same data via the leaderboards to recreate a Fully Operational simulation:
github.com/bwoodrum3/ws...
To do this, I implemented the Heckman correction method using a custom likelihood in PyMC. Details here!
github.com/justinochoi/...
Bat speed aging curve comparing two methods, one with no correction for age and another that corrects for age (fewer younger players and older players)
Bat speed aging curve, but this time I account for the fact that we are less likely to observe very young/old players. The corrected curve declines less rapidly early and more rapidly later compared to the regular curve, which seems like the correct inference:
Game 6 ends on a game-winning double play. The Dodgers managed to escape the ninth inning and force a Game 7.
Incredible stuff.
Alex spots a baseball player and in disbelief, she clasps her hands to the sides of her face and says "WOW! Trey Yesavage! You're my hero!" Trey Yesavage points to himself with this thumb and nonchalantly states "I was born after 9/11. Alex's face rapidly ages, melting into a heap of loose skin and wrinkles. John Schneider grabs Yesaage by the shoulder and says "Kid, you gotta stop introducing yourself to people that way."
Is AWS being down an omen about the fate of the Mariners
Alright third of the way there, keep it up boys
Game state when Sal Frelick came up B8, which says to keep Snell in.
Game state at the end of the inning, which says to pull Snell.
Gotta give props to last year’s #SMTDataChallenge winners, who created the Snell Tool (snelltool.com), which tells when to pull the starting pitcher. Tried it with Snell just now, and it said to pull him after the 8th. Looks like Dave Roberts agrees!
Yeah just gonna need Yamamoto, Ohtani, and Glasnow to throw CGSOs. Thanks
how about "projection onto the vector space spanned by the columns of the data"
{gm} - Create music with R: flujoo.github.io/gm/
#RStats bookmark from old twitter
This is arguably somewhat a team effect, since different teams will have different reports on what pitches to throw to whom (which the catchers use)
Would be interesting to see if this effect persists even if a catchers switches teams
The 2026 Big Data Bowl #BigDataBowl is live!
Participants can sign up for two competitions:
- leaderboard
- traditional analytics competition
This year's task: predict/understand player movement when the ball is in the air
running mcmc satisfies my dopamine cravings
60 home runs for Cal Raleigh. Incredible.
Why did Luis García Jr. get fooled so badly on this pitch?
In my article representation of my SaberSeminar presentation, I answer just that and explain how visual uncertainty influences pitch tracking and helps to explain swings.
Link below.
www.mlb.com/video/luis-g...
I don't think it will make *that* much of a difference because the normal approximation to everything is good enough, but this is definitely more flexible and rigorous!
An example of the "generalized" dynamic dead zone, using Edwin Diaz's 2024 sliders. There are contour plots of his actual slider movement, conditional movement given release characteristics using the DDZ method, and the same thing, but with the GDDZ.
Working on a "generalized" version of dynamic dead zone (DDZ) that doesn't require any assumptions about the variables' distributions. You only need to specify the covariance structure, which is Gaussian for the sake of convenience:
Every so often we check in on the models
