Loading Events
  • This event has passed.

Easy Bayes with rstanarm and brms

November 15 @ 4:00 pm - 6:00 pm

Modern Languages Building (MLB), Room 2001A

This talk will demonstrate how to turn some standard analyses into Bayesian extensions with the rstanarm and brms packages.  Basic regression and mixed models will serve as the basis for demonstrating typical options within both packages, including exploring results, model comparison, model diagnostics and more.

The goal is to show the ease of doing standard models within the Bayesian framework, hopefully providing the confidence to do more there, and realize the potential to expand into models that handle more complexity.

Prereq: Some basic modeling experience with R.  This is not an introduction to Bayesian inference, and will only dwell on various issues at a very high level, though a very brief overview will be provided at the beginning.  The document at the link below would provide enough background, but even without experience with Bayesian analysis, you may be interested in the modeling possibilities these packages offer.

Link: https://m-clark.github.io/bayesian-basics/

Details

Date:
November 15
Time:
4:00 pm - 6:00 pm
Event Category:

Organizer

CSCAR
Email:
cscar@umich.edu
Website:
cscar.research.umich.edu

Other

Register
Presenter(s)
Michael Clark