Diagnostic Modeling with R and Stan

Diagnostic classification models (DCMs; also known as cognitive diagnostic models) have gained interest in the fields of educational assessment in recent years due to their ability to provide fine-grained actionable feedback while keeping test lengths short. In this workshop, we will cover how to easily estimate and evaluate DCMs with Stan and the R package measr. The measr package includes convenience functions for creating Stan scripts, estimating models, and extract relevant pieces of model output. The workshop will include hands-on examples of defining a DCM, estimating the model, and evaluating the fit (e.g., test- and item-level fit, classification accuracy and consistency, etc.).

The goal of the workshop is to enable participants to implement DCMs in their own work, and thus is intended for anyone who uses, or would like to use, DCMs for applied or research uses (e.g., psychometricians, faculty, applied researchers, graduate students). Although not necessary, prior experience with R will be helpful. All workshop materials, including slides, examples, and solutions will be available on a workshop website. Participants should have access to a laptop they can bring to the workshop in order to follow along with the examples. Instructions for installing any necessary software will be provided.