ABSTRACT
Models with latent trajectory classes are useful when interest lies in categorizing patterns of response in treatment studies or types of developmental trajectories. This chapter introduces two commonly used methods for latent class growth analysis: latent class growth models (LCGM) and growth mixture models (GMM). Both approaches aim to classify individuals into distinct groups (classes) based on the response patterns over time so that individuals within a group are more similar than individuals in different groups. Since LCGM are a special case of GMM one can argue that they also rely on the assumption of the existence of distinct trajectory classes in the population. The chapter describes LCGM and GMM with their advantages and disadvantages. It focuses on model fitting and model selection issues and provides a couple of data examples. The chapter concludes with a summary and reiteration of the versatility and caveats of these approaches.
