Bayesian latent variable modeling in education research

Session Type: Training Session

Abstract

The goal of the session is to provide background on Bayesian latent variable modeling and to illustrate the models using education data. We will consider factor analysis models, item response models, structural equation models, and two-level variations, with distinctions between the models becoming especially blurry under a Bayesian viewpoint. Specific topics include theoretical background, advantages and disadvantages of adopting a Bayesian modeling approach, prior and posterior checking, model estimation, and model extension. The topics will be illustrated via case studies in R, especially focusing on the blavaan package paired with Stan. Session attendees are assumed to have some knowledge of item response and/or structural equation models, though not necessarily in depth.

Sub Unit

• Training Sessions

Session Organizer

• Edgar Merkle