C'est fantastique l'info trafic en temps réel de #STAN à #Nancy : maintenant que TwitiX (#Twitter) est un feu de poubelle, impossible de lire quoi que ce soit. Par contre je découvre qu'en 2021 #SaintNicolas a utilisé le réseau pour distribuer des oranges, qu'en 2022 un agresseur a été arrêté...
L'info trafic en temps réel vous disais-je ? Plutôt "Souvenirs de STAN" !
#Stan #nancy #twitter #saintnicolas
Finally a #Stan implementation for the full #DriftDiffusionModel
Looking forward to get some chains running (hopefully for not too long)
https://link.springer.com/article/10.3758/s13428-023-02179-1
I don't think I shared this: I wrote a short paper for the last ICCM/Mathpsych (https://mathpsych.org/presentation/998#/document).
It's a computational model of self-paced reading (written in @mcmc_stan) in a framework of continuous flow of information.
@cognition @linguistics @psycholinguistics @cogsci #psycholinguistics #bayesian #stan #rstats #cogsci #psycholinguistics #ComputationalModeling
#ComputationalModeling #cogsci #rstats #Stan #bayesian #psycholinguistics
New version of cmdstanr exposes Stan functions and allows you to directly unconstrain parameters (super useful for seeing parameters as the sampler sees them)! A huge win!
#rstats #bayes #mcmc_stan #cmdstanr #Stan
Updated preprint on validating that your Bayesian model and/or sampling algorithm is working correctly.
https://arxiv.org/abs/2211.02383
Thread about the first version: https://fediscience.org/@modrak_m/109301390042254531
We've added a section where we use SBC to build an ordered-simplex data type for Stan. We've also done minor improvements based on reviewer feedback and thanks to F. Saad alerting us that we misrepresented their work previously (my fault).
Thx @avehtari and all other co-authors not on here.
#Bayesian #SBC #Stan
Samozřejmě, že @danusenerudova je nejlepší volba na eurokomisařku za #stan
Osobně to rozhodně podporuji! 👏👏👏
🐦🔗: https://n.respublicae.eu/TomasZdechovsky/status/1660729084891090951
Multa kysyttiin tännään, että koska viimeksi olen käynyt erään tietyn pariskunnan luona kyläsä? En ole käyny koskaan heillä. Kysyjä oli olettanut, että me käyään toistemme luona kyläsä, ko tollaan toisen osapuolen kans saman työnantajan palaveluksesa ja asutaan samasa kerrostalosa.
Tota noi...En muutenkaan ole kyläilijätyyppiä; harvan päästän luokseni ja lähes yhtä harvan luona käyn kylässä. On muitaki tapoja tavata ystäviään/kavereita. Etenki ko suurimmaksi osaksi assuu #stan kaukana
5 cosas que debes saber de la serie “Enjambre” (Swarm)
Por fin algo nuevo en series de terror. Tal vez ya hayas visto muchas películas de este género y estés deseando que por fin
https://afrofeminas.com/2023/03/18/5-cosas-que-debes-saber-de-la-serie-enjambre-swarm/
#Actualidad #Cultura,CineyTelevisión #afrodescendientes #Afroféminas #AmazonPrime #Beyoncé #Beyonce #BillieEilish #diáspora #DominiqueFishback #DonaldGlover #Enjambre #fandom #mujernegra #seriestv #stan #Swarm #terror
#actualidad #cultura #afrodescendientes #afrofeminas #amazonprime #beyonce #billieeilish #diaspora #dominiquefishback #donaldglover #enjambre #fandom #mujernegra #seriestv #Stan #swarm #terror
I am looking for
a) examples of tools that let you build statistical models more complex then just variations of a single model class (like most stat packages - brms, laavan, ...) but less complex than fully fledged probabilistic programming languages
b) Probabilistic programming languages that neatly support composing non-trivial submodels together
Does anyone have recs?
In both cases I am coming up almost empty handed...
#brms #ProbabilisticProgramming #ppl #Stan
We have experimental Support for the symlog-normal distribution in bayesfam. A continuous unbounded transformed normal distribution using the symlog link from https://arxiv.org/abs/2301.04104 .
Seems to be able to fit skewed- as well as pointy assymetric-laplace style data.
https://github.com/sims1253/bayesfam/pull/14
I have a failing r-cmd-check action on windows in https://github.com/sims1253/bayesfam/actions/runs/4127622915/jobs/7131466283 that cries about `Error in `sink(type = "output")`: invalid connection` and seemingly has something to do with rtools and/or tbb. Does anyone have experience with Gh actions for packages that rely on rstan? @rstats #stan
Thank you for the talks @MarekVyborny, @kducsl, #STAN, @TOP09 colleagues. Congratulations to everyone who made the Czech Presidency a success story. War, migration, the US Inflation Reduction Act. We must give European answers for a safe and prosperous future for our people.
🐦🔗: https://n.respublicae.eu/ManfredWeber/status/1618583190486274048
So this lady on the train had decided her bags needed their own seat on this full train.
And then this other woman got on, came over to sit in what looked from a distance like an empty seat, then just stood there and STARED very pointedly at the bags until the other woman moved them onto her lap.
She sat down, and I stan. 🤣 #OnTheTrain #PublicTransport #stan
#onthetrain #publictransport #Stan
@rlmcelreath I attended this course 2 years ago and it has changed the way I view statistical inference, how I think about doing analyses, as well as how to teach complex mathematical concepts in an understandable way. 10/10, would recommend! Adding some tags so that it may reach more interested people #causalinference #bayes #bayesian #teaching #statistics #stats #r #stan
#Stan #r #stats #statistics #teaching #bayesian #bayes #CausalInference
Looking for a last minute holiday gift? Or just something with which to treat yourself? Give the gift of statistical education, https://events.eventzilla.net/e/principled-bayesian-modeling-with-stan-2138571624!
Or find something they'd actually appreciate and then sign them up.
#Stan #bayes #modeling #statistics
I #Stan Teddy Roosevelt and I am not apologetic about it.
(of course, he left the #Republican party)
A belated #Introduction
I'm Jesse Wolfhagen. I call myself a "Bayesian Zooarchaeologist" because I use Bayesian statistics to model different aspects of animal data from archaeological sites: from probabilistic taxonomic IDs to the age/sex composition of an assemblage to season of birth.
I am Interested in critically examining the way we view domestication processes and tell narratives about the past.
I also (try to) build rigorous statistical models for archaeology using #rstats and #Stan
To analyse the data, we implemented Bayesian phylogenetic #metaanalysis models in #stan. We developed them based on helpful advice from here https://bookdown.org/content/3890/missing-data-and-other-opportunities.html#summary-bonus-meta-analysis and the rethinking materials from @rlmcelreath https://github.com/rmcelreath/stat_rethinking_2023
The approach gave the same results as metafor (phew), but the models allowed more flexibility, for example to better understand how effects differ across the phylogeny and to look at ->