Statistical Methods Course Description
This is a short course on longitudinal “person-centered” data analysis. Topics include traditional latent transition analysis (i.e., LTA with categorical indicators), multiple group LTA, higher-order LTA, longitudinal measurement invariance testing, modern stepwise methods for modeling predictors, moderators, and outcomes of latent class transitions, and associative LTA (ALTA). Hands-on practice with Mplus is provided. Note: This is an intermediate course and will assume participants already have command of traditional cross-sectional latent class analysis techniques (see “Audience” link for more information regarding course prerequisites).
This 2.5-day mini-camp is an intensive short course in the fundamentals of latent transition analysis in Mplus.
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 manifest 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. In a longitudinal context, measures of latent class membership are repeated over time, and individual-level change and/or stability in latent class membership across time can be modeled using a latent transition analysis.
This course will introduce participants to the prevailing “best practices” for direct applications of basic finite mixture modeling to longitudinal categorical data, specifically latent transition analysis (LTA), in terms of model assumptions, specification, estimation, evaluation, selection, and interpretation. Conditional latent transition models that allow for the inclusion of predictors of latent class membership across time and moderators of latent transitions will be presented, including the most recent “stepwise” or “3-step” models. Multiple group LTA and longitudinal measurement invariance testing will be discussed. Higher-order LTA models (a.k.a. hidden latent Markov chains) as well as associative LTA (ALTA) models that allow the simultaneous modeling of parallel transition processes will also be presented. The course will touch briefly on some multilevel and times series extensions of LTA, 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 course.
Instructor: Katherine Masyn
Katherine is an Associate Professor of Biostatistics at Georgia State University’s School of Public Health. She was previously on the faculty at the Harvard Graduate School of Education and received her doctorate in Social Research Methodology at UCLA under the mentorship of Prof. Bengt Muthén. Dr. Masyn’s research focuses on the development and application of latent variable statistical models related to: survival and event history analysis; multivariate and multifaceted longitudinal processes, e.g., latent transition growth mixture models; and, more broadly, the characterization and parameterization of both observed and unobserved population heterogeneity in cross-sectional and longitudinal settings, e.g., factor mixture models. Dr. Masyn enjoys close collaborations with colleagues from the fields of Human Development, Education, Psychology, Public Health, and Prevention Science and is known for her enthusiastic instruction on applied latent variable techniques for substantive audiences.
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 Mplus will be given temporary access to a cloud server with a fully functioning version 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 course materials, including PowerPoint slides, Mplus scripts, output files, relevant supporting documentation, and recommended readings.
If you are interested in learning longitudinal “person-centered” statistical modeling techniques that can examine individual-level change and/or stability in latent subgroup (latent class) membership over time, this course is for you. You should have a good working knowledge of the principles and practice of multiple linear regression, binary logistic regression, multinomial logistic regression, and elementary statistical inference. You must have previous experience with cross-sectional latent class analysis in Mplus (equivalent to the content covered in the Applied Latent Class Analysis mini-camp). This is an intermediate course and will assume participants already have command of traditional LCA techniques. A brief review will be provided at the onset of the course but this will not provide a sufficient foundation for the course without the prerequisite knowledge. Previous experience with factor analysis and SEM is not required but would be beneficial. You do not need to know matrix algebra or likelihood theory. 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 course.