Including auxiliary variables such as antecedent and consequent variables in mixture models provides valuable insight in understanding the population heterogeneity embodied by a latent class variable. The model building process regarding how to include predictors/correlates and outcomes of the latent class variables into mixture models is an area of active research. As such, new methods of including these variables continue to emerge and best practices for the application of these methods in real data settings (including simple guidelines for choosing amongst them) are still not well established. This paper focuses on one type of auxiliary variable—distal outcomes—providing an overview of the methods currently available for estimating the effects of latent class membership on subsequent distal outcomes. We illustrate the recommended methods in the software packages Mplus and Latent Gold using a latent class model to capture population heterogeneity in students’ mathematics attitudes, linking latent class membership to two distal outcomes.
Latent transition analysis (LTA), also referred to as latent Markov modeling, is an extension of latent class/profile analysis (LCA/LPA) used to model the interrelations of multiple latent class variables. LTA methods have become increasingly accessible and in-turn are being utilized in applied research. The current article provides an introduction to LTA by answering 10 questions commonly asked by applied researchers. Topics discussed include: (1) an overview of LTA; (2) a comparison of LTA to other longitudinal models; (3) software used to run LTA; (4) sample size suggestions; (5) modeling steps in LTA; (6) measurement invariance; (7) the inclusion of auxiliary variables; (8) interpreting results of an LTA; (9) the nature of data (e.g., longitudinal, cross-sectional); and (10) extensions of LTA. An applied example of LTA is included to help understand how to build an LTA and interpret results. Finally, the article suggests future areas of research for LTA. This article provides an overview of LTA, highlighting key decisions researchers need to make to navigate and implement an LTA analysis from start to finish. (PsycInfo Database Record (c) 2023 APA, all rights reserved).
9 June 2014 in Structural Equation Modeling: A Multidisciplinary Journal
The 3-step method for estimating the effects of auxiliary variables (i.e., covariates and distal outcome) in mixture modeling provides a useful way to specify complex mixture models. One of the benefits of this method is that the measurement parameters of the mixture model are not influenced by the auxiliary variable(s). In addition, it allows for models that involve multiple latent class variables to be specified without each part of the model influencing the others. This article describes a unique latent transition analysis model where the measurement models are a latent class analysis model and a growth mixture model. We highlight the application of this model to study kindergarten readiness profiles and link it to elementary students’ reading trajectories. Mplus syntax for the 3-step specification is provided.
22 September 2016 in Structural Equation Modeling: A Multidisciplinary Journal
For some time, there have been differing recommendations about how and when to include covariates in the mixture model building process. Some have advocated the inclusion of covariates after enumeration, whereas others recommend including them early on in the modeling process. These conflicting recommendations have led to inconsistent practices and unease in trusting modeling results. In an attempt to resolve this discord, we conducted a Monte Carlo simulation to examine the impact of covariate exclusion and misspecification of covariate effects on the enumeration process. We considered population and analysis models with both direct and indirect paths from the covariates to the latent class indicators. As expected, misspecified covariate effects most commonly led to the overextraction of classes. Findings suggest that the number of classes could be reliably determined using the unconditional latent class model, thus our recommendation is that class enumeration be done prior to the inclusion of covariates.