[74] Bayesian Data Analysis with BRMS (Bayesian Regression Models Using Stan) (Mitzi Morris)

Join our Meetup group for more events! https://www.meetup.com/data-umbrella Mitzi Morris: Bayesian Data Analysis with BRMS (Bayesian Regression Models Using Stan) Full transcript: https://blog.dataumbrella.org/mitzi-brms Resources - https://github.com/generable/workshop-materials/raw/master/presentations/Bayesian_Multilevel_Modeling_brms_Stan.pdf - Mitzi's talk info: https://github.com/mitzimorris/brms_feb_28_2023 - Mitzi's talk on Software Engineering https://www.seevid.ir/fa/w/INXMncbt09g - R-Ladies New York: https://www.rladiesnyc.org/ - https://paul-buerkner.github.io/brms/articles/index.html - https://xcelab.net/rm/statistical-rethinking/ - https://journal.r-project.org/archive/2018/RJ-2018-017/RJ-2018-017.pdf - https://www.barelysignificant.com/slides/RGUG2019/#1 - https://ourcodingclub.github.io/tutorials/brms - https://onlinelibrary.wiley.com/doi/pdf/10.1111/eth.13225 - https://mc-stan.org/users/documentation/case-studies/tutorial_rstanarm.html About the Event In this webinar Mitzi Morris shows how you can quickly build robust models for data analysis and prediction using BRMS. After a brief overview of the the advantages and limitations of BRMS and a quick review of multi-level regression, we will work through an R-markdown notebook together, to see how to fit, visualize, and test the goodness of the model and resulting estimates. Timestamps https://www.seevid.ir/fa/w/A1NWoKQhgJE R-Ladies NYC Intro https://www.seevid.ir/fa/w/A1NWoKQhgJE Data Umbrella Intro https://www.seevid.ir/fa/w/A1NWoKQhgJE Speaker Introduction - Mitzi Morris https://www.seevid.ir/fa/w/A1NWoKQhgJE What is BRMS? (Bayesian Regression Models Using Stan) https://www.seevid.ir/fa/w/A1NWoKQhgJE Three reasons to use BRMS https://www.seevid.ir/fa/w/A1NWoKQhgJE Bayesian Workflow Overview https://www.seevid.ir/fa/w/A1NWoKQhgJE Modeling Terminology and Notation https://www.seevid.ir/fa/w/A1NWoKQhgJE Multilevel Regression https://www.seevid.ir/fa/w/A1NWoKQhgJE Regression Models in R & brief recent history of Bayesian programming languages https://www.seevid.ir/fa/w/A1NWoKQhgJE Linear Regression https://www.seevid.ir/fa/w/A1NWoKQhgJE Generalized Linear Regression https://www.seevid.ir/fa/w/A1NWoKQhgJE Regression Formula Syntax in BRMS https://www.seevid.ir/fa/w/A1NWoKQhgJE BRMS Processing Steps https://www.seevid.ir/fa/w/A1NWoKQhgJE Notebook - link to online notebook and data https://www.seevid.ir/fa/w/A1NWoKQhgJE Demo - in Markdown (.rmd) https://www.seevid.ir/fa/w/A1NWoKQhgJE Load packages (readr, ggplot2, brms, bayesplot, loo, projprod, cmdstanr) https://www.seevid.ir/fa/w/A1NWoKQhgJE Book - ARM https://www.seevid.ir/fa/w/A1NWoKQhgJE Example - Multilevel hierarchical model (with EPA radon dataset) https://www.seevid.ir/fa/w/A1NWoKQhgJE Further description of radon https://www.seevid.ir/fa/w/A1NWoKQhgJE Regression model https://www.seevid.ir/fa/w/A1NWoKQhgJE Demo - data example https://www.seevid.ir/fa/w/A1NWoKQhgJE 3 Modeling Choices https://www.seevid.ir/fa/w/A1NWoKQhgJE Choice 1 - Complete Pooling Model (simple linear regression formula) https://www.seevid.ir/fa/w/A1NWoKQhgJE Choice 2 - No Pooling Model (not ideal) https://www.seevid.ir/fa/w/A1NWoKQhgJE Choice 3 - Partial Pooling Model https://www.seevid.ir/fa/w/A1NWoKQhgJE Q&A - How to compare the different models? (run loo) https://www.seevid.ir/fa/w/A1NWoKQhgJE Q&A - Does BRMS have options for checking model assumptions? https://www.seevid.ir/fa/w/A1NWoKQhgJE Q&A What were the default priors? (student T-distribution with 3 degrees of freedom) https://www.seevid.ir/fa/w/A1NWoKQhgJE References About the Speaker Mitzi Morris is a member of the Stan Development Team and serves on the Stan Governing Body. Since 2017 she has been a full-time Stan developer, working for Professor Andrew Gelman at Columbia University, where she has contributed to the core Stan C++ platform and developed CmdStanPy, a modern Python interface for Stan. She is also as an active Stan user, developing, publishing, and presenting on Bayesian models for disease mapping. Prior to that she has worked as a software engineer in both academia and industry, working on natural language processing and search applications as well as data analysis pipelines for genomics and bioinformatics. - GitHub: https://github.com/mitzimorris #bayesian #statistics #rstats

• #science_technology
• #python
• #data_science
• #machine_learning
• #open_source
• #analytics
• #data_visualization
• #rstats
• #oss