Aki Vehtari
LightNews LightNews
avehtari.bsky.social
Aki Vehtari
@avehtari.bsky.social
6.3K followers 250 following 250 posts
Academy Professor in computational Bayesian modeling at Aalto University, Finland. Bayesian Data Analysis 3rd ed, Regression and Other Stories, and Active Statistics co-author. #mcmc_stan and #arviz developer.

Web page https://users.aalto.fi/~ave/
Posts Replies Media Videos
Pinned
avehtari.bsky.social
Aki Vehtari @avehtari.bsky.social · Aug 2
All three books I've co-authored are freely available online for non-commercial use:

- #Bayesian Data Analysis, 3rd ed (aka BDA3) at stat.columbia.edu/~gelman/book/

- #Regression and Other Stories at avehtari.github.io/ROS-Examples/

- Active Statistics at avehtari.github.io/ActiveStatis...
The cover of Bayesian Data Analysis book The cover of Regression and Other Stories book The cover of Active Statistics book
Reposted by Aki Vehtari
solomonkurz.bsky.social
The 1.3.0 version of my {brms} + {tidyverse} translation of Kruschke's "Doing Bayesian data analysis" is up!

solomon.quarto.pub/dbda2

#rstats

1/8
Doing Bayesian Data Analysis in brms and the tidyverse
solomon.quarto.pub
January 2, 2026 at 5:00 PM
Reposted by Aki Vehtari
alex-andorra.bsky.social
This one is a foundational one: #ExperimentalTrialDesign the ̶r̶i̶g̶h̶t̶ Bayesian way, with no other than Scott Berry, from Berry Consultants, LLC!

Enjoy, and happy new year, my dear Bayesians 🖖
learnbayesstats.bsky.social Pierre-Simon Laplace @learnbayesstats.bsky.social · 2d
Clinical trials don’t fail because patients fail.
They fail when designs stop learning.

Episode 148 of Learning Bayesian Statistics explores adaptive & platform trials and why "wait for the final analysis" isn’t neutral in ALS or pandemics.

🔗 learnbayesstats.com/episode/148-...

#newEpisode #bayes
January 2, 2026 at 11:16 AM
Reposted by Aki Vehtari
darrenjw.bsky.social
Some lecture notes on spatial and temporal modelling, illustrated using R - darrenjw.github.io/spatio-tempo... - #rstats #rspatial #quarto
Spatial and temporal statistics
darrenjw.github.io
January 1, 2026 at 12:31 PM
Reposted by Aki Vehtari
mansmag.bsky.social
🔥 First Keynote and Program committe for StanCon 2026 🔥

We present Anna Dreber (Stockholm School of Economics) as the first keynote speaker

More information can be found here:
Announcing StanCon 2026 First Keynote and Program Committee
StanCon 2026 will take place 17–21 August 2026 in Uppsala, Sweden - details at https://stancon2026.org First Keynote Confirmed Speaker Anna Dreber (Stockholm School of Economics) (Predicting) replic...
discourse.mc-stan.org
December 22, 2025 at 8:34 AM
Reposted by Aki Vehtari
ellisinstitute.fi
ELLIS Institute Finland offers:
🎓 Professorship affiliation at partner university in 🇫🇮
💻 Access to world-class computing infrastructure @lumi-supercomputer.eu
🧠 Europe's best AI + machine learning researchers as colleagues in the @ellis.eu network.
Join us! www.ellisinstitute.fi/PI-recruit-2...
Text: We're hiring! Principal Investigators in artificial intelligence and machine learning research. Below: ELLIS Institute Finland logo
December 19, 2025 at 9:07 AM
Reposted by Aki Vehtari
dingdingpeng.the100.ci
Just gave my last talk of the year!

2025 was quite packed, I gave talks about:
- the age-period-cohort problem
- making rigorous causal inference more mainstream
- mediation analysis
- marginaleffects
- causal graphs (x10)

If you're curious, check out my slides here: juliarohrer.com/resources/
Resources
Here you can find a collection of things that may be helpful, including slide decks, a curated list of introductory papers and blog posts, as well as some infographics I have generated to explain v…
juliarohrer.com
December 18, 2025 at 12:38 PM
Reposted by Aki Vehtari
rmcelreath.bsky.social
The Max Planck Society has begun an exploratory round table for open science. We are drafting some recommendations to leadership. Still a long way to go! But here are my notes on the most recent draft, just so you all know how I am trying to steer things.
Richard McElreath: It must not be overlooked that junior researchers DO NOT TRUST US. We, the directors, are a big part of the problem. We made this system, we remake it every year, and we benefit from it. What can we do to credibly signal our commitment to reform a corrupt research culture? My conversations with junior scientists in the society has taught me that directors are too often either indifferent or hostile to science reform. We cannot hope to convince our prize winning colleagues. Their egos are immune. But we can replace retirements with researchers who care more about integrity than their own prestige. This is important both for earning the trust of the junior researchers who really do the research in the MPG and for attracting excellent future directors and starting to earn the trust of the public. So I suggest two strong signals to our junior researchers (and the public): (1) we will reform recruitment and promotion at all levels to eliminate proxies like citation counts and journal brands in favor of reliability and sustainability; (2) we will make open science skills a core part of scientific training, through the graduate schools at a minimum, as conditions for the central funding. The most ambitious thing we could do, as hinted at in item 5 above, is to meaningfully invest in metascientific research. As the largest basic research organization in the world, the MPG is uniquely suited to studying research and its products from a broad perspective that includes the humanities, the sciences, and policy. Governments are already involved in science reform. Someone should study it in an organized and sustained way.
December 17, 2025 at 11:33 AM
Reposted by Aki Vehtari
jukkasuomela.fi
We are hiring an Assistant Professor in computer science! This is a broad call, all areas of computer science will be considered! We are in particular interested in datacenter-scale computing systems.
www.aalto.fi/en/open-posi...
Assistant Professor in Computer Science | Aalto University
Candidates applying to this call are considered for Assistant Professor position only. Applicants are required to have a doctoral degree and a publication track record in top journals and conferences in a relevant field.
www.aalto.fi
December 17, 2025 at 1:43 PM
avehtari.bsky.social
We're doing the final sprint, and I think we're able to send the PDF of the forthcoming Bayesian Workflow book to the publisher in the next two weeks (500+ pages), which would mean it would be published some time next year
December 16, 2025 at 5:21 PM
Reposted by Aki Vehtari
ericnovik.bsky.social
CVCT 2025 and Bayesian Model Guiding Iterative, Personalized Anticoagulant Dosing Decision-Making www.generable.com/post/cvct-2025
CVCT 2025 and Bayesian Model Guiding Iterative, Personalized Anticoagulant Dosing Decision-Making | Eric Novik | Generable
ENGAGE AF-TIMI 48 Trial Reanalysis
www.generable.com
December 15, 2025 at 7:38 PM
Reposted by Aki Vehtari
ellisinstitute.fi
1 month until deadline! Join us to build your own lab in AI + machine learning research. World-class resources incl. @lumi-supercomputer.eu, generous starting package & professorship affiliation with a university in the world’s happiest country! ➡️ www.ellisinstitute.fi/PI-recruit-2...
#hiring
Text: We're hiring! Principal Investigators in artificial intelligence and machine learning research. Below: ELLIS Institute Finland logo
December 12, 2025 at 12:11 PM
Reposted by Aki Vehtari
brian.gawalt.com
Putting together a weekly book club for "Regression and Other Stories" (reply if interested!) and this page, "Common statistical tests are linear models," is a key motivation. If you git gud at regression, so much else comes along for free.
lindeloev.github.io/tests-as-lin...

#statsky
Common statistical tests are linear models (or: how to teach stats)
lindeloev.github.io
December 11, 2025 at 9:17 PM
Reposted by Aki Vehtari
A slew of improvements to NUTS
statmodeling.stat.columbia.edu/2025/12/11/a...
A slew of improvements to NUTS | Statistical Modeling, Causal Inference, and Social Science
statmodeling.stat.columbia.edu
December 11, 2025 at 8:37 PM
Reposted by Aki Vehtari
Seven-parameter drift-diffusion pdfs and cdfs now in Stan
statmodeling.stat.columbia.edu/2025/12/11/s...
Seven-parameter drift-diffusion pdfs and cdfs now in Stan | Statistical Modeling, Causal Inference, and Social Science
statmodeling.stat.columbia.edu
December 11, 2025 at 9:00 PM
avehtari.bsky.social
All the material for my Bayesian Data Analysis course is available online, including the lectures, which we re-recorded this fall (some of them by @aloctavodia.bsky.social and Noa Kallioinen while I was on vacation). The video links are listed in the schedule at avehtari.github.io/BDA_course_A...
Bayesian Data Analysis course - Aalto 2025 – Bayesian Data Analysis course
avehtari.github.io
December 11, 2025 at 2:20 PM
Reposted by Aki Vehtari
mansmag.bsky.social
🔥 StanCon 2026 registration and abstract submission are now open! 🔥

Please spread the word!

discourse.mc-stan.org/t/stancon-20...
StanCon 2026 registration and abstract submission is now open
Hi everyone! Registration for StanCon 2026 in Uppsala, Sweden, is now open! You can already register and submit abstracts for contributions. Our first keynote speaker will be announced soon. New thi...
discourse.mc-stan.org
December 11, 2025 at 12:58 PM
avehtari.bsky.social
A nice set of examples illustrating "Complementary strengths of the Neyman-Rubin and graphical causal frameworks"
arxiv-stat-me.bsky.social arxiv.stat.ME @arxiv-stat-me.bsky.social · 23d
Tetiana Gorbach, Xavier de Luna, Juha Karvanen, Ingeborg Waernbaum
Complementary strengths of the Neyman-Rubin and graphical causal frameworks
https://arxiv.org/abs/2512.09130
December 11, 2025 at 11:55 AM
Reposted by Aki Vehtari
mc-stan.org
If you have a background in deploying Bayesian models at large or small scale for an organization and you would like to speak about it, please see this post by Brian Parbhu discourse.mc-stan.org/t/new-2025-2...
New 2025/2026 event for Bayesian Data Analysis Meetup
Hey all, I hope all is well with everyone and as we round out the year something I’ve been talking about more lately is how do we deploy and get Bayesian models into production. Depending on the fra...
discourse.mc-stan.org
December 10, 2025 at 8:33 AM
avehtari.bsky.social
New projpred (projection predictive variable selection for brms and rstanarm) release 2.10.0. Frank Weber added support for censored observations when using the latent projection (see a vignette mc-stan.org/projpred/art...). @aloctavodia.bsky.social fixed bugs and made the release.
Latent projection predictive feature selection
mc-stan.org
December 10, 2025 at 8:44 AM
Reposted by Aki Vehtari
rmcelreath.bsky.social
I'm teaching Statistical Rethinking again starting Jan 2026. This time with live lectures, divided into Beginner and Experienced sections. Will be a lot more work for me, but I hope much better for students.

I will record lectures & all will be found at this link: github.com/rmcelreath/s...
course schedule as a table. Available at the link in the post.
December 9, 2025 at 1:58 PM
avehtari.bsky.social
I'm forced to check Turnitin Similarity and AI report for MSc theses I supervise. A thesis was flagged with "An attempt to hinder similarity detection by replacing characters with similar looking ones from different alphabets or character sets." Flagged parts were equations with Greek letters!
December 5, 2025 at 1:55 PM
Reposted by Aki Vehtari
mc-stan.org
@bronder.deals's CppCon talk gives a nice overview of C++ implementation of Stan's autodiff
December 5, 2025 at 1:22 PM
Reposted by Aki Vehtari
mc-stan.org
Brmspy: Python-first access to brms (cmdstanr backend, ArviZ output) by Braffolk discourse.mc-stan.org/t/brmspy-pyt...
Brmspy: Python-first access to brms (cmdstanr backend, ArviZ output)
Hi all. I wanted to share a Python interface I’ve been building for brms that may be useful for anyone who works across both R and Python environments. brmspy provides a Python-side API for fitting b...
discourse.mc-stan.org
December 4, 2025 at 11:26 AM
Reposted by Aki Vehtari
ericnovik.bsky.social
Beware of lower limits of detection or quantification by Nikolas Siccha
www.generable.com/post/lloqs
Lower limits of detection or quantification | Nikolas Siccha | Generable
Where more data can be bad (if you don’t handle them right)
www.generable.com
December 3, 2025 at 9:04 PM
avehtari.bsky.social
In March 2024 I was reading R docs and learned 🧵

1. doc for NaN and is.nan() says: "‘NaN’ means ‘Not a Number’" and "NA, ‘_Not Available_’ which is not a number as well"

-> so neither is "a number".
December 3, 2025 at 9:19 AM