Modeling latent growth with multiple indicators: A comparison of three approaches.

Publisher Website
Google Scholar
Abstract
Latent growth curve models (LGCMs) are widely used methods for analyzing change in psychology and the social sciences. To date, most applications use first-order (single-indicator) LGCMs. These models have several limitations that can be overcome with multiple-indicator LGCMs. Currently, almost all multiple-indicator applications use the so-called second-order growth model (SGM; McArdle, 1988). In this article, we review the SGM and discuss 2 alternative, but less well-known, multiple-indicator LGCMs that overcome some of the limitations of the SGM: the generalized second-order growth model (GSGM) and the indicator-specific growth model (ISGM). In contrast to the SGM, the GSGM does not involve a proportionality constraint on the ratio of general to specific variance. The ISGM allows researchers to model indicator-specific growth. Both of these alternative models allow testing measurement invariance across time for state-variability components. We also present an empirical application regarding changes in self-reported levels of anxiety and discuss implications of the differences between the 3 models for applied research.

This publication has 0 references indexed in Scilit: