I am working with growth mixture modeling and identified a model with 4 latent classes. I know want to predict membership of those classes by several predictors - how can I implement this in R? I dont want that the priorly identified classes change through adding predictors (which is the case when adding predictors with the classmb =~ xx command).
Anyone experienced with this? I used the hlme() and then gridsearch() command.
Thank you! Michelle