Applied Bayesian Models for Social Scientists: From Theory to Estimation and Inference


  • Johannes Karreth, Ursinus College

This workshop will be offered in an online video format.

This course provides an applied introduction to Bayesian data analysis and inference, geared toward participants from the social sciences. Bayesian methods have rapidly grown in the social sciences in recent years and have become a central tool for a wide variety of analytical methods, such as multilevel and measurement models, quantitative text analysis, and network analysis. The goal of this course is to enable participants to immediately use Bayesian tools in their own research and to effectively communicate their Bayesian results to other social science scholars.

Course topics include foundations of Bayesian inference, Bayesian inference for linear and generalized linear regression models, multilevel modeling, measurement/latent variable models, and more. Upon completion of this course, participants will be able to:

  • Understand the origins and logic behind Bayesian inference
  • Use Bayesian methods for analyzing continuous and categorical outcomes in a regression framework
  • Use Bayesian methods for measurement models
  • Communicate Bayesian estimation results to practitioners and social science audiences

To allow participants to take full advantage of Bayesian data analysis in their own work, the course also teaches participants how to use the free and open-source software packages R and Stan. A set of software functions to implement some of the methods encountered in the course will also be provided.

Practical examples and applied exercises form an integral part of the course. Participants will have the opportunity to use data from their own projects for assignments during the course if applicable.

Target audience: social scientists of any discipline working with observational or experimental data. The course will be of particular benefit to researchers working on measurement issues, analyses of grouped, structured, nested, or multilevel data or repeated measures, and those interested in evaluating uncertainty around statistical indicators.

Prerequisites: Participants should have a working knowledge of regression and hypothesis testing. Prior experience with maximum likelihood estimation is useful but not required. Prior experience with R is useful but not required; assignments and labs will introduce participants to the R and Stan languages.

Registration Fee: Members = $1,500; Non-members = $3,000

Course Sections

Section 1

Location: Online -- Video format,

Date(s): June 15 - June 19

Time: 9:00 AM - 5:00 PM


  • Johannes Karreth, Ursinus College