These pages are currently under construction and will be based on content from The Methodology Center at Penn State.
Latent class modeling refers to a group of techniques for identifying unobservable, or latent, subgroups within a population. Methods like latent class analysis (LCA) and latent transition analysis (LTA) have been developed and expanded by a variety of researchers over the last two decades. LCA identifies unobservable subgroups within a population based on multiple observed indicators (e.g., multiple self-reported risk factors). Current research in the social, behavioral, and health sciences focuses on expanding methods to include latent class variables in larger models of complex developmental processes. This research allows scientists to better understand, for example, the impact of exposure to patterns of multiple risk factors, as well as the antecedents and consequences of complex behaviors, so that interventions can be tailored to target the subgroups that will benefit most. LTA is a related method that allows scientists to estimate movement between subgroups over time.
latent class analysis (LCA): profiles of teen sex and drug use
latent transition analysis (LTA): changes in teen sexual risk profiles
programming code repository for SAS, Mplus, and Latent Gold
SAS PROC LCA & PROC LTA
SAS macros for PROC LCA
LCA Stata plug-in
recommended reading list
videos and podcasts
teachers’ corner: materials for graduate-level methods courses
latent class analysis FAQ and ask a methodologist
PROC LCA & PROC LTA FAQ
latent class analysis with an outcome
latent class moderation
multilevel latent class analysis
latent class analysis and causal inference
substance use and other addictive behaviors
risk and protective factors
Portions of this website and the related scientific research were funded by National Institute on Drug Abuse awards P50 DA039838 and P50 DA010075 to The Methodology Center at Penn State.