Learning Bayesian Statistics

Get a 30% discount on Todd's book by entering the code BDABNS22 at checkout!The behavioral and neural sciences are a nerdy interest of mine, but I didn’t dedicate any episode to that topic yet. But life brings you gifts sometimes (especially around Christmas…), and here that gift is a book, Bayesian Data Analysis for the Behavioral and Neural Sciences, by Todd Hudson.Todd is a part of the faculty at New York University Grossman School of Medicine and also the New York University Tandon School of Engineering. He is a computational neuroscientist working in several areas including: early detection and grading of neurological disease; computational models of movement planning and learning; development of new computational and experimental techniques. He also co-founded Tactile Navigation Tools, which develops navigation aids for the visually impaired, and Third Eye Technologies, which develops low cost laboratory- and clinical-grade eyetracking technologies.As you’ll hear, Todd wanted his book to bypass the need for advanced mathematics normally considered a prerequisite for this type of material. Basically, he wants students to be able to write code and models and understand equations, even they are not specialized in writing those equations.We’ll also touch on some of the neural sciences examples he’s got in the book, as well as the two general algorithms he uses for model measurement and model selection.Ow, I almost forgot the most important: Todd loves beekeeping and gardening — he’s got 25 apple trees, 4 cherry trees, nectarines, figs, strawberries, etc!Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work at https://bababrinkman.com/ !Thank you to my Patrons for making this episode possible!Yusuke Saito, Avi Bryant, Ero Carrera, Brian Huey, Giuliano Cruz, Tim Gasser, James Wade, Tradd Salvo, Adam Bartonicek, William Benton, Alan O'Donnell, Mark Ormsby, Demetri Pananos, James Ahloy, Robin Taylor, Thomas Wiecki, Chad Scherrer, Nathaniel Neitzke, Zwelithini Tunyiswa, Elea McDonnell Feit, Bertrand Wilden, James Thompson, Stephen Oates, Gian Luca Di Tanna, Jack Wells, Matthew Maldonado, Ian Costley, Ally Salim, Larry Gill, Joshua Duncan, Ian Moran, Paul Oreto, Colin Caprani, George Ho, Colin Carroll, Nathaniel Burbank, Michael Osthege, Rémi Louf, Clive Edelsten, Henri Wallen, Hugo Botha, Vinh Nguyen, Raul Maldonado, Marcin Elantkowski, Adam C. Smith, Will Kurt, Andrew Moskowitz, Hector Munoz, Marco Gorelli, Simon Kessell, Bradley Rode, Patrick Kelley, Rick Anderson, Casper de Bruin, Philippe Labonde, Matthew McAnear, Michael Hankin, Cameron Smith, Luis Iberico, Alejandro Morales, Tomáš Frýda, Ryan Wesslen, Andreas Netti, Riley King, Aaron Jones and Daniel Lindroth.Visit https://www.patreon.com/learnbayesstats to unlock exclusive Bayesian swag ;)Links from the show:30% discount on Todd's book by entering BDABNS22 at checkout: https://www.cambridge.org/it/academic/subjects/psychology/psychology-general-interest/bayesian-data-analysis-behavioral-and-neural-sciences-non-calculus-fundamentals?format=PB&isbn=9781108812900Book's webpage: https://www.hudsonlab.org/textbookFor blurbs on each chapter: https://www.hudsonlab.org/textbookresourcesCode used in each chapter: https://www.hudsonlab.org/textbook/f314aFor tutorials on Bayesian vs. classical frequentist data analysis: https://www.hudsonlab.org/datatutorialsTodd's research: https://www.hudsonlab.org/researchTodd's webpage: https://med.nyu.edu/faculty/todd-e-hudsonFor information on Todd's assistive technology work: feeltnt.com

Did I mention I like survey data, especially in the context of electoral forecasting? Probably not, as I’m a pretty shy and reserved man. Why are you laughing?? Yeah, that’s true, I’m not that shy… but I did mention my interest for electoral forecasting already!And before doing a full episode where I’ll talk about French elections (yes, that’ll come at one point), let’s talk about one of France’s neighbors — Germany. Our German friends had federal elections a few weeks ago — consequential elections, since they had the hard task of replacing Angela Merkel, after 16 years in power.To talk about this election, I invited Marcus Gross on the show, because he worked on a Bayesian forecasting model to try and predict the results of this election — who will get elected as Chancellor, by how much and with which coalition?I was delighted to ask him about how the model works, how it accounts for the different sources of uncertainty — be it polling errors, unexpected turnout or media events — and, of course, how long it takes to sample (I think you’ll be surprised by the answer). We also talked about the other challenge of this kind of work: communication — how do you communicate uncertainty effectively? How do you differentiate motivated reasoning from useful feedback? What were the most common misconceptions about the model?Marcus studied statistics in Munich and Berlin, and did a PhD on survey statistics and measurement error models in economics and archeology. He worked as a data scientist at INWT, a consulting firm with projects in different business fields as well as the public sector. Now, he is working at FlixMobility.Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work at https://bababrinkman.com/ !Thank you to my Patrons for making this episode possible!Yusuke Saito, Avi Bryant, Ero Carrera, Brian Huey, Giuliano Cruz, Tim Gasser, James Wade, Tradd Salvo, Adam Bartonicek, William Benton, Alan O'Donnell, Mark Ormsby, Demetri Pananos, James Ahloy, Robin Taylor, Thomas Wiecki, Chad Scherrer, Nathaniel Neitzke, Zwelithini Tunyiswa, Elea McDonnell Feit, Bertrand Wilden, James Thompson, Stephen Oates, Gian Luca Di Tanna, Jack Wells, Matthew Maldonado, Ian Costley, Ally Salim, Larry Gill, Joshua Duncan, Ian Moran, Paul Oreto, Colin Caprani, George Ho, Colin Carroll, Nathaniel Burbank, Michael Osthege, Rémi Louf, Clive Edelsten, Henri Wallen, Hugo Botha, Vinh Nguyen, Raul Maldonado, Marcin Elantkowski, Adam C. Smith, Will Kurt, Andrew Moskowitz, Hector Munoz, Marco Gorelli, Simon Kessell, Bradley Rode, Patrick Kelley, Rick Anderson, Casper de Bruin, Philippe Labonde, Matthew McAnear, Michael Hankin, Cameron Smith, Luis Iberico, Alejandro Morales, Tomáš Frýda, Ryan Wesslen, Andreas Netti, Riley King and Aaron Jones.Visit https://www.patreon.com/learnbayesstats to unlock exclusive Bayesian swag ;)Links from the show:German election forecast website: https://www.wer-gewinnt-die-wahl.de/enTwitter account of electoral model: https://twitter.com/GerElectionFcstGerman election model code: https://github.com/INWTlab/lsTerm-election-forecastLBS #27 -- Modeling the US Presidential Elections, with Andrew Gelman & Merlin Heidemanns: https://www.learnbayesstats.com/episode/27-modeling-the-us-presidential-elections-with-andrew-gelman-merlin-heidemanns

Aubrey Clayton, a mathematician at Harvard Extension School, explores the shortcomings of standard statistical methods and their impact on various fields, from science to law. He discusses his book, "Bernoulli's Fallacy," revealing a critical error in logic that contributes to the replication crisis in modern science. Clayton highlights the transformative power of Bayesian thinking and shares insights from E.T. Jaynes, advocating for a shift in how we understand and apply probability. He emphasizes the necessity of incorporating prior knowledge to improve decision-making and scientific inference.

Folks, this is the 50th episode of LBS — 50th! I never would have thought that there were so many Bayesian nerds in the world when I first interviewed Osvaldo Martin more than 2 years ago. To celebrate that random, crazy adventure, I wanted to do a special episode at any random point, and so it looks like it’s gonna be #50! This episode is special by its guest, not its number — although my guest knows a thing or two about numbers. Most recently, he wrote the book Covid by Numbers.A mathematical statistician dedicated to helping the general public understand risk, uncertainty and decision-making, he’s the author of several books on the topic actually, including The Art of Statistics. You may also know him from his podcast, Risky Talk, or his numerous appearances in newspapers, radio and TV shows.Did you guess who it is?Maybe you just know him as the reigning World Champion in Loop – a version of pool played on an elliptical table – and are just discovering now that he is a fantastic science communicator – something that turns out to be especially important for stats education in times of, let’s say, global pandemic for instance.He holds a PhD in Mathematical Statistics from the University of London and has been the Chair of the Winton Centre for Risk and Evidence Communication at Cambridge University since 2016. He was also the President of the famous Royal Statistical Society in 2017-2018.Most importantly, he was featured in BBC1’s Winter Wipeout in 2011 – seriously, go check it out on his website; it’s hilarious.So did you guess it yet? Yep, my guest for this episode is no other than Sir David Spiegelhalter — yes, there are Bayesian knights!Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work at https://bababrinkman.com/ !Thank you to my Patrons for making this episode possible!Yusuke Saito, Avi Bryant, Ero Carrera, Brian Huey, Giuliano Cruz, Tim Gasser, James Wade, Tradd Salvo, Adam Bartonicek, William Benton, Alan O'Donnell, Mark Ormsby, Demetri Pananos, James Ahloy, Jon Berezowski, Robin Taylor, Thomas Wiecki, Chad Scherrer, Nathaniel Neitzke, Zwelithini Tunyiswa, Elea McDonnell Feit, Bertrand Wilden, James Thompson, Stephen Oates, Gian Luca Di Tanna, Jack Wells, Matthew Maldonado, Ian Costley, Ally Salim, Larry Gill, Joshua Duncan, Ian Moran, Paul Oreto, Colin Caprani, George Ho, Colin Carroll, Nathaniel Burbank, Michael Osthege, Rémi Louf, Clive Edelsten, Henri Wallen, Hugo Botha, Vinh Nguyen, Raul Maldonado, Marcin Elantkowski, Tim Radtke, Adam C. Smith, Will Kurt, Andrew Moskowitz, Hector Munoz, Marco Gorelli, Simon Kessell, Bradley Rode, Patrick Kelley, Rick Anderson, Casper de Bruin, Philippe Labonde, Matthew McAnear, Michael Hankin, Cameron Smith, Luis Iberico, Alejandro Morales and Tomáš Frýda.Visit https://www.patreon.com/learnbayesstats to unlock exclusive Bayesian swag ;)Links from the show:David's website: http://www.statslab.cam.ac.uk/~david/David on Twitter: https://twitter.com/d_spiegelThe Art of Statistics: https://dspiegel29.github.io/ArtofStatistics/Risky Talk podcast: https://riskytalk.libsyn.com/Winton Centre for Risk and Evidence Communication: https://wintoncentre.maths.cam.ac.uk/Frank Ramsey -- A Sheer Excess of Powers: https://www.amazon.fr/Frank-Ramsey-Sheer-Excess-Powers/dp/019875535XBBC Radio 4, David Spiegelhalter on Frank Ramsey: https://www.bbc.co.uk/programmes/m000q8pqDe Finetti's theorem: https://en.wikipedia.org/wiki/De_Finetti%27s_theoremLaplace's demon: https://en.wikipedia.org/wiki/Laplace%27s_demonGame of Loop: http://www.loop-the-game.com/scoop/

It’s been a while since I did an episode about sports analytics, right? And you know it’s a field I love, so… let’s do that!For this episode, I was happy to host Ehsan Bokhari, not only because he’s a first-hour listener of the podcast and spread the word about it whenever he can, but mainly because he knows baseball analytics very well!Currently Senior Director of Strategic Decision Making with the Houston Astros, he previously worked there as Senior Director of Player Evaluation and Director of R&D. And before that, he was Senior Director at the Los Angeles Dodgers from the 2015 to the 2018 season.Among other things, we talked about what his job looks like, how Bayesian the field is, which pushbacks he gets, and what the future of baseball analytics look like to him.Ehsan also has an interesting background, coming from both psychology and mathematics. Indeed, he received a PhD in quantitative psychology and an MS in statistics at the University of Illinois in 2014.Maybe most importantly, he loves reading non-fiction and spending time with his almost three-year-old son — who he read Bayesian Probability for Babies to, of course.Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work at https://bababrinkman.com/ !Thank you to my Patrons for making this episode possible!Yusuke Saito, Avi Bryant, Ero Carrera, Brian Huey, Giuliano Cruz, Tim Gasser, James Wade, Tradd Salvo, Adam Bartonicek, William Benton, Alan O'Donnell, Mark Ormsby, Demetri Pananos, James Ahloy, Jon Berezowski, Robin Taylor, Thomas Wiecki, Chad Scherrer, Nathaniel Neitzke, Zwelithini Tunyiswa, Elea McDonnell Feit, Bertrand Wilden, James Thompson, Stephen Oates, Gian Luca Di Tanna, Jack Wells, Matthew Maldonado, Ian Costley, Ally Salim, Larry Gill, Joshua Duncan, Ian Moran, Paul Oreto, Colin Caprani, George Ho, Colin Carroll, Nathaniel Burbank, Michael Osthege, Rémi Louf, Clive Edelsten, Henri Wallen, Hugo Botha, Vinh Nguyen, Raul Maldonado, Marcin Elantkowski, Tim Radtke, Adam C. Smith, Will Kurt, Andrew Moskowitz, Hector Munoz, Marco Gorelli, Simon Kessell, Bradley Rode, Patrick Kelley, Rick Anderson, Casper de Bruin, Philippe Labonde, Matthew McAnear, Michael Hankin, Cameron Smith, Luis Iberico, and Alejandro Morales.Visit https://www.patreon.com/learnbayesstats to unlock exclusive Bayesian swag ;)Links from the show:Ehsan on LinkedIn: https://www.linkedin.com/in/ebokhari/Bayesian Bagging to Generate Uncertainty Intervals -- A Catcher Framing Story: https://www.baseballprospectus.com/news/article/38289/bayesian-bagging-generate-uncertainty-intervals-catcher-framing-story/ Jim Albert's Bayesball blog: https://bayesball.github.io/Simulation of empirical Bayesian methods, using baseball statistics: http://varianceexplained.org/r/simulation-bayes-baseball/Detection and Characterization of Cluster Substructure -- Fuzzy c-Lines: https://epubs.siam.org/doi/abs/10.1137/0140029Tensor rank decomposition: https://en.wikipedia.org/wiki/Tensor_rank_decompositionStatistical Prediction versus Clinical Prediction -- Improving What Works: https://meehl.umn.edu/sites/meehl.umn.edu/files/files/155dfm1993.pdfClinical Versus Actuarial Judgment: https://meehl.umn.edu/sites/meehl.umn.edu/files/files/138cstixdawesfaustmeehl.pdfClinical Versus Statistical Prediction: https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.693.6031&rep=rep1&type=pdf

In episode 40, we already got a glimpse of how useful Bayesian stats are in the speech and communication sciences. To talk about the frontiers of this field (and, as it happens, about best practices to make beautiful plots and pictures), I invited TJ Mahr on the show.A speech pathologist turned data scientist, TJ earned his PhD in communication sciences and disorders in Madison, Wisconsin. On paper, he was studying speech development, word recognition and word learning in preschoolers, but over the course of his graduate training, he discovered that he really, really likes programming and working with data – we’ll of course talk about that in the show!In short, TJ wrangles data, crunches numbers, plots pictures, and fits models to study how children learn to speak and communicate. On his website, he often writes about Bayesian models, mixed effects models, functional programming in R, or how to plot certain kinds of data.He also got very into the deck-building game “Slay the Spire” this year, and his favorite youtube channel is a guy who restores paintings.Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work at https://bababrinkman.com/ !Thank you to my Patrons for making this episode possible!Yusuke Saito, Avi Bryant, Ero Carrera, Brian Huey, Giuliano Cruz, Tim Gasser, James Wade, Tradd Salvo, Adam Bartonicek, William Benton, Alan O'Donnell, Mark Ormsby, Demetri Pananos, James Ahloy, Jon Berezowski, Robin Taylor, Thomas Wiecki, Chad Scherrer, Nathaniel Neitzke, Zwelithini Tunyiswa, Elea McDonnell Feit, Bertrand Wilden, James Thompson, Stephen Oates, Gian Luca Di Tanna, Jack Wells, Matthew Maldonado, Ian Costley, Ally Salim, Larry Gill, Joshua Duncan, Ian Moran, Paul Oreto, Colin Caprani, George Ho, Colin Carroll, Nathaniel Burbank, Michael Osthege, Rémi Louf, Clive Edelsten, Henri Wallen, Hugo Botha, Vinh Nguyen, Raul Maldonado, Marcin Elantkowski, Tim Radtke, Adam C. Smith, Will Kurt, Andrew Moskowitz, Hector Munoz, Marco Gorelli, Simon Kessell, Bradley Rode, Patrick Kelley, Rick Anderson, Casper de Bruin, Philippe Labonde, Matthew McAnear, Michael Hankin, Cameron Smith, and Luis Iberico.Visit https://www.patreon.com/learnbayesstats to unlock exclusive Bayesian swag ;)Links from the show:TJ's website: https://www.tjmahr.com/TJ on Twitter: https://twitter.com/tjmahrTJ on GitHub: https://github.com/tjmahrLBS #40, Bayesian Stats for the Speech & Language Sciences: https://www.learnbayesstats.com/episode/40-bayesian-stats-speech-language-sciences-allison-hilger-timo-roettgerRandom Effects and Penalized Splines: https://www.tjmahr.com/random-effects-penalized-splines-same-thing/Bayes’s theorem in three panels: https://www.tjmahr.com/bayes-theorem-in-three-panels/Another mixed effects model visualization: https://www.tjmahr.com/another-mixed-effects-model-visualization/Anatomy of a logistic growth curve: https://www.tjmahr.com/anatomy-of-a-logistic-growth-curve/R Users Will Now Inevitably Become Bayesians: https://thinkinator.com/2016/01/12/r-users-will-now-inevitably-become-bayesians/Wisconsin Intelligibility, Speech, and Communication Laboratory: https://kidspeech.wisc.edu/Longitudinal Growth in Intelligibility of Connected Speech From 2 to 8 Years in Children With Cerebral Palsy: https://pubs.asha.org/doi/abs/10.1044/2020_JSLHR-20-00181Statistics for Hackers: https://speakerdeck.com/jakevdp/statistics-for-hackersStructure and interpretation of computer programs: https://mitpress.mit.edu/sites/default/files/sicp/index.htmlLectures for structure and interpretation of computer programs from 1986 (that are still very good): https://www.youtube.com/playlist?list=PLE18841CABEA24090bayesplot: https://mc-stan.org/bayesplot/ggdist: https://mjskay.github.io/ggdist/brms: https://paul-buerkner.github.io/brms/targets: https://books.ropensci.org/targets/mgcv: https://cran.r-project.org/web/packages/mgcv/index.htmllme4: https://cran.r-project.org/web/packages/lme4/index.html

The field of physics has brought tremendous advances to modern Bayesian statistics, especially inspiring the current algorithms enabling all of us to enjoy the Bayesian power on our own laptops.I did receive some physicians already on the show, like Michael Betancourt in episode 6, but in my legendary ungratefulness I hadn’t dedicated a whole episode to talk about physics yet.Well that’s now taken care of, thanks to JJ Ruby. Apart from having really good tastes (he’s indeed a fan of this very podcast), JJ is currently a postdoctoral fellow for the Center for Matter at Atomic Pressures at the University of Rochester, and will soon be starting as a Postdoctoral Scholar at Lawrence Livermore National Laboratory, a U.S. Department of Energy National Laboratory.JJ did his undergraduate work in Astrophysics and Planetary Science at Villanova University, outside of Philadelphia, and completed his master’s degree and PhD in Physics at the University of Rochester, in New York.JJ studies high energy density physics and focuses on using Bayesian techniques to extract information from large scale physics experiments with highly integrated measurements.In his freetime, he enjoys playing sports including baseball, basketball, and golf.Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work at https://bababrinkman.com/ !Thank you to my Patrons for making this episode possible!Yusuke Saito, Avi Bryant, Ero Carrera, Brian Huey, Giuliano Cruz, Tim Gasser, James Wade, Tradd Salvo, Adam Bartonicek, William Benton, Alan O'Donnell, Mark Ormsby, Demetri Pananos, James Ahloy, Jon Berezowski, Robin Taylor, Thomas Wiecki, Chad Scherrer, Nathaniel Neitzke, Zwelithini Tunyiswa, Elea McDonnell Feit, Bertrand Wilden, James Thompson, Stephen Oates, Gian Luca Di Tanna, Jack Wells, Matthew Maldonado, Ian Costley, Ally Salim, Larry Gill, Joshua Duncan, Ian Moran, Paul Oreto, Colin Caprani, George Ho, Colin Carroll, Nathaniel Burbank, Michael Osthege, Rémi Louf, Clive Edelsten, Henri Wallen, Hugo Botha, Vinh Nguyen, Raul Maldonado, Marcin Elantkowski, Tim Radtke, Adam C. Smith, Will Kurt, Andrew Moskowitz, Hector Munoz, Marco Gorelli, Simon Kessell, Bradley Rode, Patrick Kelley, Rick Anderson, Casper de Bruin, Philippe Labonde, Matthew McAnear, Michael Hankin and Cameron Smith.Visit https://www.patreon.com/learnbayesstats to unlock exclusive Bayesian swag ;)Links from the show:Center for Matter at Atomic Pressures: https://www.rochester.edu/cmap/Laboratory for Laser Energetics: https://www.lle.rochester.edu/index.php/about-the-laboratory-for-laser-energetics/Lawrence Livermore National Laboratory: https://www.llnl.gov/JJ's thesis -- Bayesian Inference of Fundamental Physics at Extreme Conditions: https://www.lle.rochester.edu/media/publications/documents/theses/Ruby.pdfRecent Fusion Breakthrough: https://www.llnl.gov/news/national-ignition-facility-experiment-puts-researchers-threshold-fusion-ignitionLBS #6, A principled Bayesian workflow, with Michael Betancourt: https://www.learnbayesstats.com/episode/6-a-principled-bayesian-workflow-with-michael-betancourt20 Best Statistics Podcasts of 2021: https://welpmagazine.com/20-best-statistics-podcasts-of-2021/E.T. Jaynes, Probability Theory -- The Logic of Science: https://www.goodreads.com/book/show/151848.Probability_TheoryD.S. Sivia, Data Analysis -- A Bayesian Tutorial: http://aprsa.villanova.edu/files/sivia.pdfS. Chandrasekhar -- An Introduction to the Study of Stellar Structure: https://www.amazon.com/Introduction-Study-Stellar-Structure-Astronomy/dp/0486604136Fun quote (from preface in Jaynes' book): Therefore we think that in the future, workers in all the quantitative sciences will be obliged, as a matter of practical necessity, to use probability theory in the manner expounded here. This trend is already well under way in several fields, ranging from econometrics to astronomy to magnetic resonance spectroscopy; but to make progress in a new area it is necessary to develop a healthy disrespect for tradition and authority, which have retarded progress throughout the 20th century.

You wanna know something funny? A sentence from this episode became a meme. And people even made stickers out of it! Ok, that’s not true. But if someone could pull off something like that, it would surely be Chelsea Parlett-Pelleriti.Indeed, Chelsea’s research focuses on using statistics and machine learning on behavioral data, but her more general goal is to empower people to be able to do their own statistical analyses, through consulting, education, and, as you may have seen, stats memes on Twitter.A full-time teacher, researcher and statistical consultant, Chelsea earned an MsC and PhD in Computational and Data Science in 2021 from Chapman University. Her courses include R, intro to programming (in Python), and data science.In a nutshell, Chelsea is, by her own admission, an avid lover of anything silly or statistical. Hopefully, this episode turned out to be both at once! I’ll let you be the judge of that…Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work at https://bababrinkman.com/ !Thank you to my Patrons for making this episode possible!Yusuke Saito, Avi Bryant, Ero Carrera, Brian Huey, Giuliano Cruz, Tim Gasser, James Wade, Tradd Salvo, Adam Bartonicek, William Benton, Alan O'Donnell, Mark Ormsby, Demetri Pananos, James Ahloy, Jon Berezowski, Robin Taylor, Thomas Wiecki, Chad Scherrer, Nathaniel Neitzke, Zwelithini Tunyiswa, Elea McDonnell Feit, Bertrand Wilden, James Thompson, Stephen Oates, Gian Luca Di Tanna, Jack Wells, Matthew Maldonado, Ian Costley, Ally Salim, Larry Gill, Joshua Duncan, Ian Moran, Paul Oreto, Colin Caprani, George Ho, Colin Carroll, Nathaniel Burbank, Michael Osthege, Rémi Louf, Clive Edelsten, Henri Wallen, Hugo Botha, Vinh Nguyen, Raul Maldonado, Marcin Elantkowski, Tim Radtke, Adam C. Smith, Will Kurt, Andrew Moskowitz, Hector Munoz, Marco Gorelli, Simon Kessell, Bradley Rode, Patrick Kelley, Rick Anderson, Casper de Bruin and Philippe Labonde.Visit https://www.patreon.com/learnbayesstats to unlock exclusive Bayesian swag ;)Links from the show:Chelsea's website: https://cmparlettpelleriti.github.io/index.htmlChelsea on Twitter: https://twitter.com/ChelseaParlettMichael Betancourt's sparsity case study: https://betanalpha.github.io/assets/case_studies/modeling_sparsity.htmlLBS #31 -- Bayesian Cognitive Modeling & Decision-Making, with Michael Lee: https://www.learnbayesstats.com/episode/31-bayesian-cognitive-modeling-michael-leeProjection predictive variable selection R package: https://mc-stan.org/projpred/SelectiveInference R package: https://cran.r-project.org/web/packages/selectiveInference/selectiveInference.pdfStatistical learning and selective inference: https://www.pnas.org/content/112/25/7629LBS #29 -- Model Assessment, Non-Parametric Models, with Aki Vehtari: https://www.learnbayesstats.com/episode/model-assessment-non-parametric-models-aki-vehtariLBS #35 -- The Past, Present & Future of BRMS, with Paul Bürkner: https://www.learnbayesstats.com/episode/35-past-present-future-brms-paul-burknerBRMS R Package: https://paul-buerkner.github.io/brms/Bayesian Item Response Modeling in R with BRMS and Stan: https://arxiv.org/pdf/1905.09501.pdfBAyesian Model-Building Interface (Bambi) in PythonBAyesian Model-Building Interface (Bambi) in Python: https://bambinos.github.io/bambi/main/index.htmlZero-one-inflated beta regression: https://twitter.com/SolomonKurz/status/1395056477459648521Ordinal Regression Models in Psychology: https://www.researchgate.net/publication/331335573_Ordinal_Regression_Models_in_Psychology_A_TutorialLBS #38 -- How to Become a Good Bayesian (& Rap Artist), with Baba Brinkman: https://www.learnbayesstats.com/episode/38-how-to-become-good-bayesian-rap-artist-baba-brinkman

As a podcaster, I discovered that there are guests for which the hardest is to know when to stop the conversation. They could talk for hours and that would make for at least 10 fantastic episodes. Frank Harrell is one of those guests. To me, our conversation was both fascinating — thanks to Frank’s expertise and the width and depth of topics we touched on — and frustrating — I still had a gazillion questions for him!But rest assured, we talked about intent to treat and randomization, proportional odds, clinical trial design, bio stats and covid19, and even which mistakes you should do to learn Bayes stats — yes, you heard right, which mistakes. Anyway, I can’t tell you everything here — you’ll just have to listen to the episode!A long time Bayesian, Frank is a Professor of Biostatistics in the School of Medicine at Vanderbilt University. His numerous research interests include predictive models and model validation, Bayesian clinical trial design and Bayesian models, drug development, and clinical research.He holds a PhD in biostatistics from the University of North Carolina, and did his Bachelor in mathematics at the University of Alabama in Birmingham.Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work at https://bababrinkman.com/ !Thank you to my Patrons for making this episode possible!Yusuke Saito, Avi Bryant, Ero Carrera, Brian Huey, Giuliano Cruz, Tim Gasser, James Wade, Tradd Salvo, Adam Bartonicek, William Benton, Alan O'Donnell, Mark Ormsby, Demetri Pananos, James Ahloy, Jon Berezowski, Robin Taylor, Thomas Wiecki, Chad Scherrer, Nathaniel Neitzke, Zwelithini Tunyiswa, Elea McDonnell Feit, Bertrand Wilden, James Thompson, Stephen Oates, Gian Luca Di Tanna, Jack Wells, Matthew Maldonado, Ian Costley, Ally Salim, Larry Gill, Joshua Duncan, Ian Moran, Paul Oreto, Colin Caprani, George Ho, Colin Carroll, Nathaniel Burbank, Michael Osthege, Rémi Louf, Clive Edelsten, Henri Wallen, Hugo Botha, Vinh Nguyen, Raul Maldonado, Marcin Elantkowski, Tim Radtke, Adam C. Smith, Will Kurt, Andrew Moskowitz, Hector Munoz, Marco Gorelli, Simon Kessell, Bradley Rode, Patrick Kelley, Rick Anderson, Casper de Bruin and Philippe Labonde.Visit https://www.patreon.com/learnbayesstats to unlock exclusive Bayesian swag ;)Links from the show:Frank's website and courses: https://hbiostat.org/Frank's blog: https://www.fharrell.com/Frank on Twitter: https://twitter.com/f2harrellCOVID-19 Randomized Clinical Trial Design: https://hbiostat.org/proj/covid19/Frank on GitHub: https://github.com/harrelfeRegression Modeling Strategies repository: https://github.com/harrelfe/rmsBiostatistics for Biomedical Research repository: https://github.com/harrelfe/bbrBayesian Approaches to Randomized Trials, Spiegelhalter et al.: http://hbiostat.org/papers/Bayes/spi94bay.pdfStatistical Rethinking, Richard McElreath: http://xcelab.net/rm/statistical-rethinking/LBS #20, Regression and Other Stories, with Andrew Gelman, Jennifer Hill & Aki Vehtari: https://www.learnbayesstats.com/episode/20-regression-and-other-stories-with-andrew-gelman-jennifer-hill-aki-vehtariDavid Spiegelhalter, The Art of Statistics -- Learning from Data: https://www.amazon.fr/Art-Statistics-Learning-Data/dp/0241398630Confidence intervals vs. Bayesian intervals, E.T. Jaynes: https://bayes.wustl.edu/etj/articles/confidence.pdf

Episode sponsored by Paperpile: paperpile.comGet 20% off until December 31st with promo code GOODBAYESIAN21Bonjour my dear Bayesians! Yes, it was bound to happen one day — and this day has finally come. Here is the first ever 100% French speaking ‘Learn Bayes Stats’ episode! Who is to blame, you ask? Well, who better than Rémi Louf?Rémi currently works as a senior data scientist at Ampersand, a big media marketing company in the US. He is the author and maintainer of several open source libraries, including MCX and BlackJAX. He holds a PhD in statistical Physics, a Masters in physics from the Ecole Normale Supérieure and a Masters in Philosophy from Oxford University.I think I know what you’re wondering: how the hell do you go from physics to philosophy to Bayesian stats?? Glad you asked, as it was my first question to Rémi! He’ll also tell us why he created MXC and BlackJax, what his main challenges are when working on open-source projects, and what the future of PPLs looks like to him.Our theme music is « Good Bayesian », by Baba Brinkman (feat MC Lars and Mega Ran). Check out his awesome work at https://bababrinkman.com/ !Thank you to my Patrons for making this episode possible!Yusuke Saito, Avi Bryant, Ero Carrera, Brian Huey, Giuliano Cruz, Tim Gasser, James Wade, Tradd Salvo, Adam Bartonicek, William Benton, Alan O'Donnell, Mark Ormsby, Demetri Pananos, James Ahloy, Jon Berezowski, Robin Taylor, Thomas Wiecki, Chad Scherrer, Nathaniel Neitzke, Zwelithini Tunyiswa, Elea McDonnell Feit, Bertrand Wilden, James Thompson, Stephen Oates, Gian Luca Di Tanna, Jack Wells, Matthew Maldonado, Ian Costley, Ally Salim, Larry Gill, Joshua Duncan, Ian Moran, Paul Oreto, Colin Caprani, George Ho, Colin Carroll, Nathaniel Burbank, Michael Osthege, Rémi Louf, Clive Edelsten, Henri Wallen, Hugo Botha, Vinh Nguyen, Raul Maldonado, Marcin Elantkowski, Tim Radtke, Adam C. Smith, Will Kurt, Andrew Moskowitz, Hector Munoz, Marco Gorelli, Simon Kessell, Bradley Rode, Patrick Kelley, Rick Anderson, Casper de Bruin and Philippe Labonde.Visit https://www.patreon.com/learnbayesstats to unlock exclusive Bayesian swag ;)Links from the show:Rémi on GitHub: https://github.com/rloufRémi on Twitter: https://twitter.com/remiloufRémi's website: https://rlouf.github.io/BlackJAX -- Fast & modular sampling library: https://github.com/blackjax-devs/blackjaxMCX -- Probabilistic programs on CPU & GPU, powered by JAX: https://github.com/rlouf/mcxaeppl, Tools for a PPL in Aesara: https://github.com/aesara-devs/aepplFrench Presidents' popularity dashboard: https://www.pollsposition.com/popularityHow to model presidential approval (in French): https://anchor.fm/pollspolitics/episodes/10-Comment-Modliser-la-Popularit-e121jh2LBS #23, Bayesian Stats in Business & Marketing, with Elea McDonnel Feit: https://www.learnbayesstats.com/episode/23-bayesian-stats-in-business-and-marketing-analytics-with-elea-mcdonnel-feitLBS #30, Symbolic Computation & Dynamic Linear Models, with Brandon Willard: https://www.learnbayesstats.com/episode/symbolic-computation-dynamic-linear-models-brandon-willard