home.social

#bayesiandataanalysis — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #bayesiandataanalysis, aggregated by home.social.

fetched live
  1. Back to topic.
    Modelling has changed and improved a lot. Mostly due to more powerful computers allowing more brute force analysis. The math tools really haven't changed that much. Early commercial modelling included programs like #Surfer decades ago and used #Kriging, (#Gaussian peocess regression) of geostatistical data. Most current geospatial modelling uses this technique, often enhanced with #BayesianDataAnalysis (read the book by that name). So now the table is mostly set. 5/

  2. Computing Bayes Factors is difficult in general. But for issues like "parameter > number", there is a nice method: _encompassing models_. It's simple, elegant and powerful, i.o.w., it's beautifully Bayesian. 🤩

    Here is an overview: tinyurl.com/3pxs2pc9

    #BDA #Bayes #BayesianDataAnalysis #ml #stats

  3. New paper on the production of verbal expressions of (uncertain) probability #xprag. Using #BayesianDataAnalysis to investigate structural properties of the latent #semantics of expressions like "probable" or "low chance" in a probabilistic model of #pragmatic utterance choice.
    Joint w/ Bob van Tiel & Uli Sauerland. #openaccess
    doi.org/10.1162/opmi_a_00066