Modules
1 - Introduction
2 - Bayesian inference for one discrete outcome
3 - Bayesian inference for one continuous outcome
4 - Deriving a posterior; bias-variance trade-off
Link to slides
Link to recording module 4
5 - Sampling
Link to slides
Link to recording module 5
6 - Sampling from posterior densities in Stan
Link to slides
Link to recording module 6
Instructions on how to get Stan and brms set up
If you want “just do this” directions… DO THIS:
Consider updating your R and Rstudio
First install Rstan in 2 steps:
configure your C++ Toolchain, instructions per operating system are here: https://github.com/stan-dev/rstan/wiki/RStan-Getting-Started#configuring-c-toolchain
install rstan and verify the installation: https://github.com/stan-dev/rstan/wiki/RStan-Getting-Started#installing-rstan
Then install the brms R package; type in your R console: install.packages(“brms”)
Then run the code in module6_brms_gettingstarted.Rmd… does it work?
Yes -> hoorah!
No -> Check if you missed some steps. If not, get help (in breakout rooms, on our slack)
If you want to figure things out for yourself, see https://github.com/paul-buerkner/brms?tab=readme-ov-file#how-do-i-install-brms and stan resources.
- Note: we will use the latest releases, NOT the developmental versions of code, unless stated otherwise (read: unless we come across a bug that’s been resolved in a developmental version)
7 and 8 - Hierarchical (or multilevel) models
In modules 7 and 8, we’re going to discuss how to exchange information between populations using hierarchical models, which are also called multilevel models, and fit such models using the brm function.
9 - Expanding your model universe
11 - Model checking and validation
12 - Bayesian workflow
Supplementary material on priors and how to set them: