Aki Vehtari
@avehtari.bsky.social
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/
Web page https://users.aalto.fi/~ave/
Pinned
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...
- #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...
Reposted by Aki Vehtari
Three weeks time to submit contributed talk abstract to StanCon 2026! You can also submit a poster abstract early, if you need to make early travel plans. There will be travel and accommodation support for students, too!
More information about submitting at www.stancon2026.org/abstracts/
More information about submitting at www.stancon2026.org/abstracts/
February 4, 2026 at 3:55 PM
Three weeks time to submit contributed talk abstract to StanCon 2026! You can also submit a poster abstract early, if you need to make early travel plans. There will be travel and accommodation support for students, too!
More information about submitting at www.stancon2026.org/abstracts/
More information about submitting at www.stancon2026.org/abstracts/
Watching @rmcelreath.bsky.social's both A and B lectures feels like a watching a movie which jumps between two different time periods
Every estimand needs an estiplan - lecture A05 of Statistical Rethinking 2026. Total and direct effects, posterior predictions and causal contrasts, sermon about model assumptions and strength of inference. Next week is a back-alley intro to do-calculus. github.com/rmcelreath/s...
Statistical Rethinking 2026 Lecture A05 - Estimands & Estiplans
YouTube video by Richard McElreath
www.youtube.com
February 4, 2026 at 7:15 PM
Watching @rmcelreath.bsky.social's both A and B lectures feels like a watching a movie which jumps between two different time periods
Reposted by Aki Vehtari
I also want to hear about your favorite recent (<5 years 😅) Stan and Stan-adjacent developments that changed your bayesian framework (thinking about models, validating models, fitting models and checking their fit and how they break)!
as I'm revising my course materials, I keep stumbling upon cool @mc-stan.org developments.
Current favorites:
1. your model has funnels and you exhausted reparametrization ideas: metric = "dense_e" makes your HMC learn about covariance btw parameters. Sloooow, but effective!
1/
Current favorites:
1. your model has funnels and you exhausted reparametrization ideas: metric = "dense_e" makes your HMC learn about covariance btw parameters. Sloooow, but effective!
1/
February 4, 2026 at 1:35 PM
I also want to hear about your favorite recent (<5 years 😅) Stan and Stan-adjacent developments that changed your bayesian framework (thinking about models, validating models, fitting models and checking their fit and how they break)!
Reposted by Aki Vehtari
as I'm revising my course materials, I keep stumbling upon cool @mc-stan.org developments.
Current favorites:
1. your model has funnels and you exhausted reparametrization ideas: metric = "dense_e" makes your HMC learn about covariance btw parameters. Sloooow, but effective!
1/
Current favorites:
1. your model has funnels and you exhausted reparametrization ideas: metric = "dense_e" makes your HMC learn about covariance btw parameters. Sloooow, but effective!
1/
February 4, 2026 at 1:30 PM
as I'm revising my course materials, I keep stumbling upon cool @mc-stan.org developments.
Current favorites:
1. your model has funnels and you exhausted reparametrization ideas: metric = "dense_e" makes your HMC learn about covariance btw parameters. Sloooow, but effective!
1/
Current favorites:
1. your model has funnels and you exhausted reparametrization ideas: metric = "dense_e" makes your HMC learn about covariance btw parameters. Sloooow, but effective!
1/
Reposted by Aki Vehtari
Reposted by Aki Vehtari
This time I try to explain group-level confounding and some ways to deal with it. Lecture B04 of Statistical Rethinking 2026 - fixed effects, Mundlak machines, latent Mundlak machines, intro to social network analysis and the social relations model. Full lecture list: github.com/rmcelreath/s...
Statistical Rethinking 2026 Lecture B04 - Group-level confounding and intro to social networks
YouTube video by Richard McElreath
www.youtube.com
January 30, 2026 at 1:27 PM
This time I try to explain group-level confounding and some ways to deal with it. Lecture B04 of Statistical Rethinking 2026 - fixed effects, Mundlak machines, latent Mundlak machines, intro to social network analysis and the social relations model. Full lecture list: github.com/rmcelreath/s...
Reposted by Aki Vehtari
wanna learn about cognitive modeling and love pizza? I am revising my cognitive modeling course notes and could use some feedback (or you might just enjoy learning about cog modeling in R and Stan): fusaroli.github.io/AdvancedCogn...
(only chapter 1-3 are in place, the others will come)
(only chapter 1-3 are in place, the others will come)
Chapter 2 The Pizza Experiment | Advanced Cognitive Modeling Notes
My notes for the advanced cognitive modeling course - 2026
fusaroli.github.io
January 30, 2026 at 9:08 AM
wanna learn about cognitive modeling and love pizza? I am revising my cognitive modeling course notes and could use some feedback (or you might just enjoy learning about cog modeling in R and Stan): fusaroli.github.io/AdvancedCogn...
(only chapter 1-3 are in place, the others will come)
(only chapter 1-3 are in place, the others will come)
Reposted by Aki Vehtari
StanCon 2026 is this August 17-21 in Upsala, Sweden 🇸🇪
www.stancon2026.org
⏰ Abstracts for contributed talks are due Feb 25
⏰ Abstracts for posters are due May 27
And just to be clear: Yes, StanCon is my favorite conference to attend!! Can't wait for this one!
www.stancon2026.org
⏰ Abstracts for contributed talks are due Feb 25
⏰ Abstracts for posters are due May 27
And just to be clear: Yes, StanCon is my favorite conference to attend!! Can't wait for this one!
January 29, 2026 at 9:55 PM
StanCon 2026 is this August 17-21 in Upsala, Sweden 🇸🇪
www.stancon2026.org
⏰ Abstracts for contributed talks are due Feb 25
⏰ Abstracts for posters are due May 27
And just to be clear: Yes, StanCon is my favorite conference to attend!! Can't wait for this one!
www.stancon2026.org
⏰ Abstracts for contributed talks are due Feb 25
⏰ Abstracts for posters are due May 27
And just to be clear: Yes, StanCon is my favorite conference to attend!! Can't wait for this one!
Reposted by Aki Vehtari
if you want to know how to compute marginal means from a mixed effects model in brms using rvars, then have I got a supplemental materials document for you pubs.asha.org/doi/10.1044/...
Does the Use of Crowdsourced Listeners Yield Different Speech Intelligibility Results Than In-Person Listeners for Typically Developing Children?
Purpose: We examined the performance of crowdsourced listeners compared with in-person
listeners on the measurement of speech intelligibility for...
pubs.asha.org
January 29, 2026 at 10:10 PM
if you want to know how to compute marginal means from a mixed effects model in brms using rvars, then have I got a supplemental materials document for you pubs.asha.org/doi/10.1044/...
Reposted by Aki Vehtari
Another absolute banger from @natehaines.bsky.social: generative hierarchical Bayesian modeling* is the best way to investigate individual differences!
*This isn't "just" making use of Bayesian estimation, but one of the best examples I've seen of a full Bayesian embrace of uncertainty.
*This isn't "just" making use of Bayesian estimation, but one of the best examples I've seen of a full Bayesian embrace of uncertainty.
1/9 New blog is live! This is part 2 of a series—last time we looked at the Dunning-Kruger effect, now we are digging in to Implicit vs Explicit attitudes and the Implicit Association Test. To start, of course we need a good meme...
haines-lab.com/post/part-2-...
haines-lab.com/post/part-2-...
January 29, 2026 at 8:08 AM
Another absolute banger from @natehaines.bsky.social: generative hierarchical Bayesian modeling* is the best way to investigate individual differences!
*This isn't "just" making use of Bayesian estimation, but one of the best examples I've seen of a full Bayesian embrace of uncertainty.
*This isn't "just" making use of Bayesian estimation, but one of the best examples I've seen of a full Bayesian embrace of uncertainty.
Reposted by Aki Vehtari
1/9 New blog is live! This is part 2 of a series—last time we looked at the Dunning-Kruger effect, now we are digging in to Implicit vs Explicit attitudes and the Implicit Association Test. To start, of course we need a good meme...
haines-lab.com/post/part-2-...
haines-lab.com/post/part-2-...
January 26, 2026 at 5:45 PM
1/9 New blog is live! This is part 2 of a series—last time we looked at the Dunning-Kruger effect, now we are digging in to Implicit vs Explicit attitudes and the Implicit Association Test. To start, of course we need a good meme...
haines-lab.com/post/part-2-...
haines-lab.com/post/part-2-...
Reposted by Aki Vehtari
All my #rstats ebooks are now in the quarto format, and hosted on Quarto Pub. Their old bookdown links will all be dead by the weekend.
1/3
1/3
January 28, 2026 at 3:34 PM
All my #rstats ebooks are now in the quarto format, and hosted on Quarto Pub. Their old bookdown links will all be dead by the weekend.
1/3
1/3
Reposted by Aki Vehtari
Deadline for StanCon 2026 tutorials and workshops (@mc-stan) is today (anywhere on earth). More information here:
discourse.mc-stan.org/t/stancon-20...
discourse.mc-stan.org/t/stancon-20...
StanCon 2026 Tutorials and Workshop deadline today (AoE)
Hi everyone, The submission deadline for contributing tutorials and workshops is today (anywhere on earth). Tutorial Tutorials provide hands-on learning experiences to help attendees build practica...
discourse.mc-stan.org
January 28, 2026 at 10:12 AM
Deadline for StanCon 2026 tutorials and workshops (@mc-stan) is today (anywhere on earth). More information here:
discourse.mc-stan.org/t/stancon-20...
discourse.mc-stan.org/t/stancon-20...
Our CS department could be a great fit for you, too! Although in the call there is interest in particular topics, all areas of CS are considered including computational Bayes, ML, AI, etc. So worth trying if working in those areas, too
Aalto University is looking for an Assistant Professor in Computer Science, application deadline February 2, 2026!
www.aalto.fi/en/open-posi...
www.aalto.fi/en/open-posi...
January 26, 2026 at 4:38 PM
Our CS department could be a great fit for you, too! Although in the call there is interest in particular topics, all areas of CS are considered including computational Bayes, ML, AI, etc. So worth trying if working in those areas, too
Bayesian Workflow by
Andrew Gelman, Aki Vehtari, @rmcelreath.bsky.social with @danpsimpson.bsky.social, @charlesm993.bsky.social, @yulingy.bsky.social, Lauren Kennedy, Jonah Gabry, @paulbuerkner.com, @modrakm.bsky.social, @vianeylb.bsky.social
(in production, estimated copy-editing time 6 weeks)
Andrew Gelman, Aki Vehtari, @rmcelreath.bsky.social with @danpsimpson.bsky.social, @charlesm993.bsky.social, @yulingy.bsky.social, Lauren Kennedy, Jonah Gabry, @paulbuerkner.com, @modrakm.bsky.social, @vianeylb.bsky.social
(in production, estimated copy-editing time 6 weeks)
January 26, 2026 at 8:18 AM
Bayesian Workflow by
Andrew Gelman, Aki Vehtari, @rmcelreath.bsky.social with @danpsimpson.bsky.social, @charlesm993.bsky.social, @yulingy.bsky.social, Lauren Kennedy, Jonah Gabry, @paulbuerkner.com, @modrakm.bsky.social, @vianeylb.bsky.social
(in production, estimated copy-editing time 6 weeks)
Andrew Gelman, Aki Vehtari, @rmcelreath.bsky.social with @danpsimpson.bsky.social, @charlesm993.bsky.social, @yulingy.bsky.social, Lauren Kennedy, Jonah Gabry, @paulbuerkner.com, @modrakm.bsky.social, @vianeylb.bsky.social
(in production, estimated copy-editing time 6 weeks)
Publisher's copy-editing for the Bayesian Workflow book has started
January 23, 2026 at 7:45 PM
Publisher's copy-editing for the Bayesian Workflow book has started
Reposted by Aki Vehtari
Adventures in Covariance - Lecture B03 of Statistical Rethinking 2026. Prelude about MCMC effective sample size, Multilevel varying slopes models with correlated features, non-centered parameterizations for covariance models, model expansion workflow. Next week is social networks.
Statistical Rethinking Lecture B03 - Adventures in Covariance
YouTube video by Richard McElreath
www.youtube.com
January 23, 2026 at 1:22 PM
Adventures in Covariance - Lecture B03 of Statistical Rethinking 2026. Prelude about MCMC effective sample size, Multilevel varying slopes models with correlated features, non-centered parameterizations for covariance models, model expansion workflow. Next week is social networks.
Juho Timonen defended his thesis succesfully 🎉 (the thesis includes two papers I helped with: speeding up ODEs with importance sampling dx.doi.org/10.1002/sta4... and longitudinal GPs doi.org/10.1093/bioi...). Photo includes supervisor Harri Lähdesmäki and the opponent @mrattray.bsky.social
January 23, 2026 at 2:14 PM
Juho Timonen defended his thesis succesfully 🎉 (the thesis includes two papers I helped with: speeding up ODEs with importance sampling dx.doi.org/10.1002/sta4... and longitudinal GPs doi.org/10.1093/bioi...). Photo includes supervisor Harri Lähdesmäki and the opponent @mrattray.bsky.social
It's this one: "(Breaking) The defaults for all geoms can be set at one in the theme" It's just not telling that the shipped themes also do set the defaults in the theme (instead of some defaults being fixed as previously). As I said, you know it's this one only with additional information
January 21, 2026 at 3:14 PM
It's this one: "(Breaking) The defaults for all geoms can be set at one in the theme" It's just not telling that the shipped themes also do set the defaults in the theme (instead of some defaults being fixed as previously). As I said, you know it's this one only with additional information
Reposted by Aki Vehtari
StanCon 2026 tutorial and workshop deadlines in one week:
discourse.mc-stan.org/t/stancon-20...
@mc-stan.org
discourse.mc-stan.org/t/stancon-20...
@mc-stan.org
StanCon 2026 Deadline for tutorial and workshop in one week
Hi everyone, The submission deadline for contributing tutorials and workshops is one week from now, on the 28th of January. Tutorial Tutorials provide hands-on learning experiences to help attendee...
discourse.mc-stan.org
January 21, 2026 at 9:20 AM
StanCon 2026 tutorial and workshop deadlines in one week:
discourse.mc-stan.org/t/stancon-20...
@mc-stan.org
discourse.mc-stan.org/t/stancon-20...
@mc-stan.org
When you know what to look, you can see it listed as a breaking change in the release notes ggplot2.tidyverse.org/news/index.h...
projpred package plots were also hit by this. It was annoying to figure what caused the change, but in the end I think it is a useful change
projpred package plots were also hit by this. It was annoying to figure what caused the change, but in the end I think it is a useful change
January 21, 2026 at 7:34 AM
When you know what to look, you can see it listed as a breaking change in the release notes ggplot2.tidyverse.org/news/index.h...
projpred package plots were also hit by this. It was annoying to figure what caused the change, but in the end I think it is a useful change
projpred package plots were also hit by this. It was annoying to figure what caused the change, but in the end I think it is a useful change
Reposted by Aki Vehtari
February 5th in Bayesian Data Analysis Meetup virtual event:
Bayesian Models in Production by Ian Costley (Wegmans Food Markets)
...hands-on experience deploying Bayesian models built with Stan and PyMC into real production systems...
see more at discourse.mc-stan.org/t/feb-5th-ba...
Bayesian Models in Production by Ian Costley (Wegmans Food Markets)
...hands-on experience deploying Bayesian models built with Stan and PyMC into real production systems...
see more at discourse.mc-stan.org/t/feb-5th-ba...
Feb 5th Bayesian Data Analysis Meetup Virtual Event
Hi All, On Feb 5 we have a virtual event for the Bayesian Data Analysis Meetup. We’re excited to host Ian Costley (Wegmans Food Markets) for an upcoming talk on Bayesian Models in Production. Ian wi...
discourse.mc-stan.org
January 20, 2026 at 12:15 PM
February 5th in Bayesian Data Analysis Meetup virtual event:
Bayesian Models in Production by Ian Costley (Wegmans Food Markets)
...hands-on experience deploying Bayesian models built with Stan and PyMC into real production systems...
see more at discourse.mc-stan.org/t/feb-5th-ba...
Bayesian Models in Production by Ian Costley (Wegmans Food Markets)
...hands-on experience deploying Bayesian models built with Stan and PyMC into real production systems...
see more at discourse.mc-stan.org/t/feb-5th-ba...
Reposted by Aki Vehtari
May 11, Short Course on Bayesian Causal Inference with Stan, Stress-Testing Assumptions: Bayesian Methods for Sensitivity Analysis in Causal Inference, in-person at the American Causal Inference Conference meeting in Salt Lake City. See more at discourse.mc-stan.org/t/upcoming-s...
Upcoming Short Course on Bayesian Causal Inference with Stan
Hi all, I wanted to publicize a short course I’ll be teaching on topics related to Bayesian causal inference. See below for course title, abstract, outline, and other information. The course will be...
discourse.mc-stan.org
January 20, 2026 at 12:19 PM
May 11, Short Course on Bayesian Causal Inference with Stan, Stress-Testing Assumptions: Bayesian Methods for Sensitivity Analysis in Causal Inference, in-person at the American Causal Inference Conference meeting in Salt Lake City. See more at discourse.mc-stan.org/t/upcoming-s...
Can you add Feather or Parquet file support? These are well supported by R, Python, Julia etc. and would provide nice way to read only some variables
January 20, 2026 at 7:09 AM
Can you add Feather or Parquet file support? These are well supported by R, Python, Julia etc. and would provide nice way to read only some variables