#48 Mixed Effects Models & Beautiful Plots, with TJ Mahr
Learning Bayesian Statistics
How Did You Become Into Basion Stats?
Tespell talks about how he got into basion stats and why they are so powerful. He says the idea that you don't need to memorize analytical formulas was a big draw for him. Testers can now wrangle their data with basic skills, allowing them to quanify uncertainty from models. The next step in his career will be working on patient tatisticic research.
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/tjmahr
- TJ on GitHub: https://github.com/tjmahr
- LBS #40, Bayesian Stats for the Speech & Language Sciences: https://www.learnbayesstats.com/episode/40-bayesian-stats-speech-language-sciences-allison-hilger-timo-roettger
- Random 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-20-00181
- Statistics for Hackers: https://speakerdeck.com/jakevdp/statistics-for-hackers
- Structure and interpretation of computer programs: https://mitpress.mit.edu/sites/default/files/sicp/index.html
- Lectures for structure and interpretation of computer programs from 1986 (that are still very good): https://www.youtube.com/playlist?list=PLE18841CABEA24090
- bayesplot: 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.html
- lme4: https://cran.r-project.org/web/packages/lme4/index.html
The AI-powered Podcast Player
