Martin Modrák
Tomasz Woźniak
Krzysztof Sakrejda
Ryan
Miss Kitty 🌈🌈🌈#MissKitty #BayesianBitch her newest #hashtag! 😹😹😹
She is getting her #Bayesian on‼️
It's actually how I think. I live in ambiguity. Is there anything else? 😹😹😹👊🏻🔦🎤💃🏻
Bayesian methodology is a statistical approach that uses Bayes' theorem to update the probability of a hypothesis as
RE: https://bsky.app/profile/did:plc:o3tr3xg2gh34qwthivey2hef/post/3mgs7ycv6r22g
RE: https://bsky.app/profile/did:plc:o3tr3xg2gh34qwthivey2hef/post/3mgs7ycv6r22g
Christophe BousquetInterested in how to study #SocialTransmission in a #Bayesian framework? Here is a paper for you in #MethodsInEcologyAndEvolution @MethodsEcolEvol:
#STbayes: An #R package for creating, fitting and understanding Bayesian models of social transmission
https://besjournals.onlinelibrary.wiley.com/doi/full/10.1111/2041-210x.70228
Sam Van Horne, Ph.D.TIL Building #Bayesian regression models with {cmdstanr} can result in a ton of large files stored in Temp on the hard drive that can clog the machine. It literally begged me to return to frequentist statistics. #rstats
Issue: https://discourse.mc-stan.org/t/deleting-temporary-files-created-by-cmdstanr/32485
Deleting temporary files created by cmdstanr
I am running cmdstanr within an mclapply loop, e.g. mod <- cmdstan_model(stan_file='myModel.stan') results <-do.call(rbind,mclapply(1:1000,mc.cores=4,function(i) { ... fit <- mod$sample(data=input_data, chains=4, parallel_chains=4) ... }) Stan runs fine but it creates several large files within the rtmpfile /tmp/RtmpXXX and they do not get removed, but actually accumulate as the mclapply loop pro...
Frederic BlumMy first solo-authored publication just appeared in *Linguistic Typology*: "The over-representation of phonological features in basic vocabulary doesn’t replicate when controlling for spatial and phylogenetic effects"
Running a #Bayesian model with #Lexibank data, I show that most previously observed effects that have been claimed to be sound symbolism do **not** replicate. A handful of effects emerges as highly stable though, mostly related to body-parts and the pronominal system.
The over-representation of phonological features in basic vocabulary doesn’t replicate when controlling for spatial and phylogenetic effects
The statistical over-representation of certain phonological features in the basic vocabulary of languages is often interpreted as reflecting potentially universal sound symbolic patterns. However, most of these cases have not been tested explicitly for reproducibility and might be prone to biases in the study samples or models. Many studies on the topic do not adequately control for genealogical and areal dependencies between sampled languages, casting doubts on the robustness of the results. In this study, I test the robustness of a recent study on sound symbolism in basic vocabulary concepts which analyzed 245 languages. This paper adds a new sample of 2,864 languages from Lexibank. I modify the original model by adding statistical controls for spatial and phylogenetic dependencies between languages. The new results show that most of the previously observed patterns are not robust, and in fact many patterns disappear completely when adding the genealogical and areal controls. A small number of patterns, however, emerges as highly stable even with the new sample. Through the new analysis, it is possible to assess the distribution of sound symbolism on a larger scale than previously. The study further highlights the need for testing all universal claims on language for robustness on various levels.
Pierre-Simon LaplaceEpisode 152 is out 🎙️
Host Alex Andorra talks with Daniel Saunders about a Bayesian decision theory workflow.
Big idea: stop optimizing for model accuracy and start optimizing for decision value.
Andrzej Wąsowski ☑️ 🟥I have spent some time cleaning up my home-grown #Bayesian inference library for public consumption. Enjoy:
https://codeberg.org/wasowski/probula
The story goes that I needed a pure Scala3 replacement for #Figaro, that I can use for teaching purposes. The status is:
- Probula can handle regression models
- Importance sampling, monadic style implementation
- Very basic descriptive stats built in.
- CVS export for arviz, to perform posterior analysis.
