Introduction to Longitudinal Diagnostic Classification Models

This event is being organized by the NCME Diagnostic Measurement SIGIMIE.

Diagnostic classification models (DCMs) are psychometrics tools that focus on providing actionable feedback in the form of examinee attribute classifications. This session builds upon a foundational understanding of DCMs and provides a more advanced coverage of DCMs. More specifically, this session focuses on longitudinal DCMs and their application as the psychometric foundation for categorical growth models. After completing this session, participants will understand the conceptual and statistical foundations of longitudinal DCMs, be able to estimate longitudinal DCMs, and interpret results from a recently developed R package.

This session is appropriate for graduate students, researchers, and practitioners at the emerging or experienced level. Participants are expected to have a basic knowledge of DCMs and psychometrics to enroll. This session presents both conceptual and technical content (3-3:25 pm) and also provides hands-on experience through empirical analyses and interpretation of results (3:25-3:50). The session will conclude with time for audience questions and discussion (3:50-4 pm).

Presenter:

• Matthew Madison is Assistant Professor of Quantitative Methodology at the University of Georgia, where he studies and teaches courses in educational measurement and statistics. His research centers around the advancement of multivariate psychometric models. More specifically, Dr. Madison has focused his research on a class of contemporary item response models called diagnostic classification models (DCMs) and their application in educational contexts. Motivated by his background in mathematics education, his research seeks to use DCMs to improve the utility of educational assessments. Recently, he has investigated longitudinal DCMs as alternatives to traditional psychometric methods for modeling learning over time. Relatedly, he led the development of the TDCM R package for estimating longitudinal DCMs.