Latent Class Growth Analysis and Growth Mixture Modeling using R: A tutorial for two R-packages and a comparison with Mplus.
Klaas J. Wardenaar
Abstract
Latent Class Growth Analyses (LCGA) and Growth Mixture Modeling (GMM) analyses are used to explain between-subject heterogeneity in growth on an outcome, by identifying latent classes with different growth trajectories. Dedicated software packages are available to estimate these models, with Mplus (Muthén & Muthén, 2019) being widely used. Although this and other available commercial software packages are of good quality, very flexible and rich in options, they can be costly and fit poorly into the analytical workflow of researchers that increasingly depend on the open-source R-platform. Interestingly, although plenty of R-packages to conduct mixture analyses are available, there is little documentation on how to conduct LCGA/GMM in R.This educational document aims to provide applied researchers with relatively little prior experience with a tutorial and coding examples for conducting LCGA and GMM in R. The results obtained with R and the modeling approaches (e.g., default settings, model configuration) of the used R-packages are compared to each other and to Mplus using simulated data.