Overview: An advanced seminar in “person-centered” longitudinal data analysis. Topics include repeated measures latent class analysis, semi-parametric group-based trajectory modeling, growth mixture modeling, latent transition analysis, associative latent transition analysis, and select extensions. Hands-on practice with Mplus is provided. This five-day summer institute is an advanced intensive short seminar in the analysis of longitudinal data using latent class analysis and finite mixture modeling. Finite mixture models are a type of latent variable model that express the overall distribution of one or more variables as a mixture of a finite number of component distributions. In direct applications, one assumes that the overall population heterogeneity with respect to a set of variables is due to the existence of two or more distinct homogeneous subgroups, or latent classes, of individuals. These approaches are often termed “person-centered” analyses in contrast to the “variable-centered” analyses of conventional factor and SEM models.
This seminar will introduce participants to the prevailing “best practices” for direct applications of mixture modeling to longitudinal data, specifically repeated measures latent class analysis (RMLCA), semi-parametric group-based trajectory analysis (a.k.a., latent class growth analysis), growth mixture modeling (GMM), latent transition analysis (LTA), and associative latent transition analysis (ALTA) in terms of model assumptions, specification, estimation, evaluation, selection, and interpretation. Growth mixture models that allow for the inclusion of correlates and predictors of latent trajectory class membership as well as distal outcomes of latent trajectory class membership will be presented. Latent transition models that allow for the inclusion of predictors of latent class membership over time, moderators of latent transitions, and higher order latent class variables (i.e., hidden Markov chain models) will be presented. The seminar will also explore model combinations (e.g., latent transition growth mixture models) and extensions (e.g., multilevel latent transition analysis, onset-to-growth mixture models, etc.) as participant interest dictates and time allows. The implementation of these models in the most recent version of the Mplus software will be demonstrated throughout the seminar.
Instructors: Jeffrey Harring Ph.D.
Dr. Harring is a Professor in the Measurement, Statistics, and Evaluation (EDMS) program in the Department of Human Development and Quantitative Methodology at the University of Maryland. Prior to joining the the EDMS faculty in the fall of 2006, Dr. Harring received a M.S. degree in Statistics in 2004, and completed his Ph.D. in the Quantitative Methods Program within Educational Psychology in 2005–both degrees coming from the University of Minnesota. Before that, Dr. Harring taught high school mathematics for 12 years.
Software and Computer Support
Participants should bring a laptop computer. Instruction will be provided for the methods using the most current version of Mplus (base program with mixture add-on or base program with combination add-on). Mplus is available for Windows, Mac, and Linux environments (www.statmodel.com).
Participants who do not have access to software will be given temporary access to the server that contains fully functioning versions of the recommended software.
Note: We will also make use of Excel and R to do various post-processing summaries.
Participants will receive an electronic copy of all seminar materials, including PowerPoint slides, Mplus scripts, output files, relevant supporting documentation, and recommended readings.
If you already have a strong background in the application of finite mixture models to cross-sectional data (e.g., latent class analysis and latent class cluster analysis) and you need to learn how to apply more advanced mixture models to longitudinal data, this seminar is for you. We strongly recommend that you attend our five-day intensive summer institute on applied latent class analysis and finite mixture modeling as a pre-requisite to taking this five-day advanced seminar. If you have not taken the foundations seminar, you should have extensive experience doing latent class analysis and/or latent profile analysis in Mplus or have taken a graduate-level seminar on latent class analysis using Mplus before enrolling. You do not need to know matrix algebra, likelihood theory, or longitudinal SEM, although knowledge of latent growth modeling in a SEM framework would be greatly beneficial. Participants from a variety of fields—including psychology, education, human development, public health, prevention science, sociology, marketing, business, biology, medicine, political science, and communication—will benefit from the seminar.