Wanted to share a video of a recent presentation by Mitzi Morris (@mitzimorris)
Bayesian Data Analysis with BRMS
BRMS=Bayesian Regression Models using Stan
💡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.
Please note that timestamps and a full transcript are now available for:
Video: Bayesian Data Analysis with BRMS (Mitzi Morris, @mitzimorris)
Full transcript
Timestamps
00:00 R-Ladies NYC Intro
04:55 Data Umbrella Intro
08:25 Speaker Introduction - Mitzi Morris
10:15 What is BRMS? (Bayesian Regression Models Using Stan)
11:15 Three reasons to use BRMS
13:51 Bayesian Workflow Overview
15:25 Modeling Terminology and Notation
17:54 Multilevel Regression
21:30 Regression Models in R & brief recent history of Bayesian programming languages
27:22 Linear Regression
28:52 Generalized Linear Regression
31:05 Regression Formula Syntax in BRMS
34:33 BRMS Processing Steps
37:13 Notebook - link to online notebook and data
37:38 Demo - in Markdown (.rmd)
38:18 Load packages (readr, ggplot2, brms, bayesplot, loo, projprod, cmdstanr)
38:38 Book - ARM
39:07 Example - Multilevel hierarchical model (with EPA radon dataset)
40:32 Further description of radon
41:37 Regression model
42:02 Demo - data example
42:26 3 Modeling Choices
44:31 Choice 1 - Complete Pooling Model (simple linear regression formula)
48:22 Choice 2 - No Pooling Model (not ideal)
50:17 Choice 3 - Partial Pooling Model
56:26 Q&A - How to compare the different models? (run loo)
01:00:00 Q&A - Does BRMS have options for checking model assumptions?
01:01:00 Q&A What were the default priors? (student T-distribution with 3 degrees of freedom)
01:05:27 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.
Connect with the Speaker
Many thanks for adding timestamps - extremely useful.
Materials for an expanded version of this tutorial that I gave at StanCon 2023 are here: StanCon 2023 Tutorial on BRMS
