home.social

#bayesian — Public Fediverse posts

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

  1. Imagine you’re evaluating a new cancer treatment. It reduces tumor size in most patients, but some experience severe side effects. Would we consider the new treatment better?

    Read more about it in a new post on superiority in the multivariate context.

    bit.ly/4e97n4n

    #statistics #bayesian #rstats

  2. 🦀 smoothbp has been submitted to CRAN!
    Hierarchical piecewise regression with smoothed change-points in — multi-breakpoint models, spike-and-slab regularisation for automatic breakpoint selection, and a fast MCMC sampler written in Rust under the hood.
    Dev version: github.com/ABindoff/smoothbp

  3. 🦀 smoothbp has been submitted to CRAN!
    Hierarchical piecewise regression with smoothed change-points in #RStats — multi-breakpoint models, spike-and-slab regularisation for automatic breakpoint selection, and a fast MCMC sampler written in Rust under the hood.
    Dev version: github.com/ABindoff/smoothbp
    #rstats #statistics #bayesian

  4. The Open Inference Lab just opened!🚀

    A place for exploring statistical models, with a focus on making complex methods more transparent and easier to understand.

    First post: How to handle multiple binary outcomes in a Bayesian way bit.ly/4ujWL8a

    #statistics #bayesian #rstats

  5. New in Demographic Research: Our Bayesian multi-dimensional mortality reconstruction integrates Eurostat, DHS, UN WPP & WIC data to flexibly estimate age-, sex-, and education-specific mortality across countries. #Bayesian #Demography #popjus #iiasa #WIC
    demographic-research.org/artic

  6. New in Demographic Research: Our Bayesian multi-dimensional mortality reconstruction integrates Eurostat, DHS, UN WPP & WIC data to flexibly estimate age-, sex-, and education-specific mortality across countries. #Bayesian #Demography #popjus #iiasa #WIC
    demographic-research.org/artic

  7. New in Demographic Research: Our Bayesian multi-dimensional mortality reconstruction integrates Eurostat, DHS, UN WPP & WIC data to flexibly estimate age-, sex-, and education-specific mortality across countries. #Bayesian #Demography #popjus #iiasa #WIC
    demographic-research.org/artic

  8. New in Demographic Research: Our Bayesian multi-dimensional mortality reconstruction integrates Eurostat, DHS, UN WPP & WIC data to flexibly estimate age-, sex-, and education-specific mortality across countries. #Bayesian #Demography #popjus #iiasa #WIC
    demographic-research.org/artic

  9. New in Demographic Research: Our Bayesian multi-dimensional mortality reconstruction integrates Eurostat, DHS, UN WPP & WIC data to flexibly estimate age-, sex-, and education-specific mortality across countries. #Bayesian #Demography #popjus #iiasa #WIC
    demographic-research.org/artic

  10. @marjolica @Simon318ppm

    ...whose birthday, incidentally, is today.

    Happy birthday, David MacKay! 🎂 🎓 🚀

    MacKay was also one of the first to make clear the connection between many machine-learning algorithms, especially neural networks, and Bayesian probability theory: <inference.org.uk/mackay/PhD.ht>.

    His book on Information Theory, Inference, and Learning Algorithms is brilliant and full of humour: <inference.org.uk/itila/book.ht>, just like his lectures: <videolectures.net/events/cours>.

    And just as brilliant is his book "Sustainable Energy – without the hot air" which analyses in a rational way our energy and climate problem: <withouthotair.com>. See also his TED talk <ted.com/talks/david_mackay_a_r>.

    He died too soon 😢

    itila.blogspot.com/
    eng.cam.ac.uk/news/professor-s

    #bayesian #probability #MachineLearning #cambridge #physics

  11. @marjolica @Simon318ppm

    ...whose birthday, incidentally, is today.

    Happy birthday, David MacKay! 🎂 🎓 🚀

    MacKay was also one of the first to make clear the connection between many machine-learning algorithms, especially neural networks, and Bayesian probability theory: <inference.org.uk/mackay/PhD.ht>.

    His book on Information Theory, Inference, and Learning Algorithms is brilliant and full of humour: <inference.org.uk/itila/book.ht>, just like his lectures: <videolectures.net/events/cours>.

    And just as brilliant is his book "Sustainable Energy – without the hot air" which analyses in a rational way our energy and climate problem: <withouthotair.com>. See also his TED talk <ted.com/talks/david_mackay_a_r>.

    He died too soon 😢

    itila.blogspot.com/
    eng.cam.ac.uk/news/professor-s

    #bayesian #probability #MachineLearning #cambridge #physics

  12. @marjolica @Simon318ppm

    ...whose birthday, incidentally, is today.

    Happy birthday, David MacKay! 🎂 🎓 🚀

    MacKay was also one of the first to make clear the connection between many machine-learning algorithms, especially neural networks, and Bayesian probability theory: <inference.org.uk/mackay/PhD.ht>.

    His book on Information Theory, Inference, and Learning Algorithms is brilliant and full of humour: <inference.org.uk/itila/book.ht>, just like his lectures: <videolectures.net/events/cours>.

    And just as brilliant is his book "Sustainable Energy – without the hot air" which analyses in a rational way our energy and climate problem: <withouthotair.com>. See also his TED talk <ted.com/talks/david_mackay_a_r>.

    He died too soon 😢

    itila.blogspot.com/
    eng.cam.ac.uk/news/professor-s

    #bayesian #probability #MachineLearning #cambridge #physics

  13. @marjolica @Simon318ppm

    ...whose birthday, incidentally, is today.

    Happy birthday, David MacKay! 🎂 🎓 🚀

    MacKay was also one of the first to make clear the connection between many machine-learning algorithms, especially neural networks, and Bayesian probability theory: <inference.org.uk/mackay/PhD.ht>.

    His book on Information Theory, Inference, and Learning Algorithms is brilliant and full of humour: <inference.org.uk/itila/book.ht>, just like his lectures: <videolectures.net/events/cours>.

    And just as brilliant is his book "Sustainable Energy – without the hot air" which analyses in a rational way our energy and climate problem: <withouthotair.com>. See also his TED talk <ted.com/talks/david_mackay_a_r>.

    He died too soon 😢

    itila.blogspot.com/
    eng.cam.ac.uk/news/professor-s

    #bayesian #probability #MachineLearning #cambridge #physics

  14. @marjolica @Simon318ppm

    ...whose birthday, incidentally, is today.

    Happy birthday, David MacKay! 🎂 🎓 🚀

    MacKay was also one of the first to make clear the connection between many machine-learning algorithms, especially neural networks, and Bayesian probability theory: <inference.org.uk/mackay/PhD.ht>.

    His book on Information Theory, Inference, and Learning Algorithms is brilliant and full of humour: <inference.org.uk/itila/book.ht>, just like his lectures: <videolectures.net/events/cours>.

    And just as brilliant is his book "Sustainable Energy – without the hot air" which analyses in a rational way our energy and climate problem: <withouthotair.com>. See also his TED talk <ted.com/talks/david_mackay_a_r>.

    He died too soon 😢

    itila.blogspot.com/
    eng.cam.ac.uk/news/professor-s

    #bayesian #probability #MachineLearning #cambridge #physics

  15. Hehehehe, we got another reviewer confused by our use of a 89% credible interval.
    Cue the beauty of prime numbers! And it is my co-author's birth year, I am so happy that I can put this in the answer 😅!

    #bayesian #academicchatter #bayes @rlmcelreath

  16. Hehehehe, we got another reviewer confused by our use of a 89% credible interval.
    Cue the beauty of prime numbers! And it is my co-author's birth year, I am so happy that I can put this in the answer 😅!

    #bayesian #academicchatter #bayes @rlmcelreath

  17. Hehehehe, we got another reviewer confused by our use of a 89% credible interval.
    Cue the beauty of prime numbers! And it is my co-author's birth year, I am so happy that I can put this in the answer 😅!

    #bayesian #academicchatter #bayes @rlmcelreath

  18. Hehehehe, we got another reviewer confused by our use of a 89% credible interval.
    Cue the beauty of prime numbers! And it is my co-author's birth year, I am so happy that I can put this in the answer 😅!

    #bayesian #academicchatter #bayes @rlmcelreath

  19. Hehehehe, we got another reviewer confused by our use of a 89% credible interval.
    Cue the beauty of prime numbers! And it is my co-author's birth year, I am so happy that I can put this in the answer 😅!

    #bayesian #academicchatter #bayes @rlmcelreath

  20. There is a high probability of there being between 5 and 9 songs in this analysis of Melbourne's weather.

    How many seasons does Melbourne really have?

    seasons.lotlsoft.com/
    The rweal question is :
    Why does the mean of all them "appear" to happen every day ? ? ?

    Nice though and way better than the Northern Hemisphere 4 thing ..

    Though it needs a bigger longer data set ?

    Hey BOM throw some "UX" Interface petty cash at this for every region in OCEANIA !

    (( and go read up on Vasa ))

    #Bayesian #analysis #weather #Melbourne #climate #indigenous
    #BOM #Australia #Vasa

  21. There is a high probability of there being between 5 and 9 songs in this analysis of Melbourne's weather.

    How many seasons does Melbourne really have?

    seasons.lotlsoft.com/
    The rweal question is :
    Why does the mean of all them "appear" to happen every day ? ? ?

    Nice though and way better than the Northern Hemisphere 4 thing ..

    Though it needs a bigger longer data set ?

    Hey BOM throw some "UX" Interface petty cash at this for every region in OCEANIA !

    (( and go read up on Vasa ))

    #Bayesian #analysis #weather #Melbourne #climate #indigenous
    #BOM #Australia #Vasa

  22. There is a high probability of there being between 5 and 9 songs in this analysis of Melbourne's weather.

    How many seasons does Melbourne really have?

    seasons.lotlsoft.com/
    The rweal question is :
    Why does the mean of all them "appear" to happen every day ? ? ?

    Nice though and way better than the Northern Hemisphere 4 thing ..

    Though it needs a bigger longer data set ?

    Hey BOM throw some "UX" Interface petty cash at this for every region in OCEANIA !

    (( and go read up on Vasa ))

    #Bayesian #analysis #weather #Melbourne #climate #indigenous
    #BOM #Australia #Vasa

  23. There is a high probability of there being between 5 and 9 songs in this analysis of Melbourne's weather.

    How many seasons does Melbourne really have?

    seasons.lotlsoft.com/
    The rweal question is :
    Why does the mean of all them "appear" to happen every day ? ? ?

    Nice though and way better than the Northern Hemisphere 4 thing ..

    Though it needs a bigger longer data set ?

    Hey BOM throw some "UX" Interface petty cash at this for every region in OCEANIA !

    (( and go read up on Vasa ))

    #Bayesian #analysis #weather #Melbourne #climate #indigenous
    #BOM #Australia #Vasa

  24. There is a high probability of there being between 5 and 9 songs in this analysis of Melbourne's weather.

    How many seasons does Melbourne really have?

    seasons.lotlsoft.com/
    The rweal question is :
    Why does the mean of all them "appear" to happen every day ? ? ?

    Nice though and way better than the Northern Hemisphere 4 thing ..

    Though it needs a bigger longer data set ?

    Hey BOM throw some "UX" Interface petty cash at this for every region in OCEANIA !

    (( and go read up on Vasa ))

    #Bayesian #analysis #weather #Melbourne #climate #indigenous
    #BOM #Australia #Vasa

  25. Defining the Computational Surface:

    ​🔹 [Level 0] - KEREN: 0 Tokens. Surface-level discovery and basic vendor identification. The "Free Look" at the gate.

    ​🔸 [Level 1] - CHARLOTTE: 1 Token. Bayesian Prior Analysis. This detects "Numerical Sickness" and generates your baseline HFY (How Fucked Are You) score.

    ​Choose your depth.

    ​#RiskEngine #DataScience #Bayesian #HFYScore #Charlotte

  26. Defining the Computational Surface:

    ​🔹 [Level 0] - KEREN: 0 Tokens. Surface-level discovery and basic vendor identification. The "Free Look" at the gate.

    ​🔸 [Level 1] - CHARLOTTE: 1 Token. Bayesian Prior Analysis. This detects "Numerical Sickness" and generates your baseline HFY (How Fucked Are You) score.

    ​Choose your depth.

    ​#RiskEngine #DataScience #Bayesian #HFYScore #Charlotte

  27. Defining the Computational Surface:

    ​🔹 [Level 0] - KEREN: 0 Tokens. Surface-level discovery and basic vendor identification. The "Free Look" at the gate.

    ​🔸 [Level 1] - CHARLOTTE: 1 Token. Bayesian Prior Analysis. This detects "Numerical Sickness" and generates your baseline HFY (How Fucked Are You) score.

    ​Choose your depth.

    ​#RiskEngine #DataScience #Bayesian #HFYScore #Charlotte

  28. Defining the Computational Surface:

    ​🔹 [Level 0] - KEREN: 0 Tokens. Surface-level discovery and basic vendor identification. The "Free Look" at the gate.

    ​🔸 [Level 1] - CHARLOTTE: 1 Token. Bayesian Prior Analysis. This detects "Numerical Sickness" and generates your baseline HFY (How Fucked Are You) score.

    ​Choose your depth.

    ​#RiskEngine #DataScience #Bayesian #HFYScore #Charlotte

  29. Defining the Computational Surface:

    ​🔹 [Level 0] - KEREN: 0 Tokens. Surface-level discovery and basic vendor identification. The "Free Look" at the gate.

    ​🔸 [Level 1] - CHARLOTTE: 1 Token. Bayesian Prior Analysis. This detects "Numerical Sickness" and generates your baseline HFY (How Fucked Are You) score.

    ​Choose your depth.

    ​#RiskEngine #DataScience #Bayesian #HFYScore #Charlotte

  30. "Five skills. Each one is counter-cyclical (becomes more valuable as hype recedes), resistant to LLM automation (requires human judgment that pattern-matching can’t replicate), and directly tied to the business outcomes executives actually pay for."
    by Kaushik Rajan: towardsdatascience.com/the-ai-

    #DataScience #BayesianStatistics #BayesianStats #Bayesian #causalInference #experimentalDesign #SPC #statisticalProcessControl

  31. "Five skills. Each one is counter-cyclical (becomes more valuable as hype recedes), resistant to LLM automation (requires human judgment that pattern-matching can’t replicate), and directly tied to the business outcomes executives actually pay for."
    by Kaushik Rajan: towardsdatascience.com/the-ai-

    #DataScience #BayesianStatistics #BayesianStats #Bayesian #causalInference #experimentalDesign #SPC #statisticalProcessControl

  32. "Five skills. Each one is counter-cyclical (becomes more valuable as hype recedes), resistant to LLM automation (requires human judgment that pattern-matching can’t replicate), and directly tied to the business outcomes executives actually pay for."
    by Kaushik Rajan: towardsdatascience.com/the-ai-

  33. "Five skills. Each one is counter-cyclical (becomes more valuable as hype recedes), resistant to LLM automation (requires human judgment that pattern-matching can’t replicate), and directly tied to the business outcomes executives actually pay for."
    by Kaushik Rajan: towardsdatascience.com/the-ai-

    #DataScience #BayesianStatistics #BayesianStats #Bayesian #causalInference #experimentalDesign #SPC #statisticalProcessControl

  34. "Five skills. Each one is counter-cyclical (becomes more valuable as hype recedes), resistant to LLM automation (requires human judgment that pattern-matching can’t replicate), and directly tied to the business outcomes executives actually pay for."
    by Kaushik Rajan: towardsdatascience.com/the-ai-

    #DataScience #BayesianStatistics #BayesianStats #Bayesian #causalInference #experimentalDesign #SPC #statisticalProcessControl

  35. Preprint alert: Simulation-based validation of Bayes Factor computation with @paul_buerkner and Sebastian Stroppel. We bring lessons learned in improving SBC to validation of Bayes factors. The main idea is still the same: simulate data from the models, fit those and see if the inferences are calibrated. 1/
    arxiv.org/abs/2508.11814
    #Bayesian #stats #rstats #SBC

  36. Preprint alert: Simulation-based validation of Bayes Factor computation with @paul_buerkner and Sebastian Stroppel. We bring lessons learned in improving SBC to validation of Bayes factors. The main idea is still the same: simulate data from the models, fit those and see if the inferences are calibrated. 1/
    arxiv.org/abs/2508.11814
    #Bayesian #stats #rstats #SBC

  37. Preprint alert: Simulation-based validation of Bayes Factor computation with @paul_buerkner and Sebastian Stroppel. We bring lessons learned in improving SBC to validation of Bayes factors. The main idea is still the same: simulate data from the models, fit those and see if the inferences are calibrated. 1/
    arxiv.org/abs/2508.11814
    #Bayesian #stats #rstats #SBC

  38. Preprint alert: Simulation-based validation of Bayes Factor computation with @paul_buerkner and Sebastian Stroppel. We bring lessons learned in improving SBC to validation of Bayes factors. The main idea is still the same: simulate data from the models, fit those and see if the inferences are calibrated. 1/
    arxiv.org/abs/2508.11814
    #Bayesian #stats #rstats #SBC

  39. Preprint alert: Simulation-based validation of Bayes Factor computation with @paul_buerkner and Sebastian Stroppel. We bring lessons learned in improving SBC to validation of Bayes factors. The main idea is still the same: simulate data from the models, fit those and see if the inferences are calibrated. 1/
    arxiv.org/abs/2508.11814
    #Bayesian #stats #rstats #SBC

  40. I'll be having a little bit of capacity for paid consulting/stats gigs in the upcoming months, so get in touch if you need some Bayesian support! #bayesian #stats #FediHire

  41. I'll be having a little bit of capacity for paid consulting/stats gigs in the upcoming months, so get in touch if you need some Bayesian support! #bayesian #stats #FediHire

  42. I'll be having a little bit of capacity for paid consulting/stats gigs in the upcoming months, so get in touch if you need some Bayesian support! #bayesian #stats #FediHire