An Extension of the General Latent Variable Growth Modeling Framework to Four Levels of the Hierarchy

Abstract

In recent years, a number of statistical techniques for the analysis of longitudinal multilevel data have become available, allowing researchers the opportunity to study behavior at different levels (e.g., individual, family, school, neighborhood). Although many of these statistical approaches are widely available, they are still relatively underused, and there is uncertainty among researchers as to the appropriateness and usefulness of different approaches for analyzing longitudinal data. The purpose of this article is to present an extension of the general latent variable growth curve modeling framework to 4 levels of the hierarchy. This 4-level extension merges 2 common analytic approaches used in answering longitudinal multilevel research questions: (a) a full information maximum likelihood (ML) latent growth modeling approach using an extension of a factor-of-curves model and (b) a limited information multilevel latent growth modeling (LGM) approach using Muthén's ML-based estimator. Data comprised repeated observations over 4 time points from 250 adolescents in 125 households and 61 geographical sampling areas. Results demonstrate comparable outcomes and interpretations derived from the hierarchical LGM extension and regression-based techniques. Discussion includes a comparison of techniques, encompassing advantages and limitations.