Many issues of interest to counseling psychologists involve questions regarding how individuals change over time. Typically, these analyses examine average levels of change over time in a sample. However, statistical methods known as latent variable growth modeling (LVGM; Muthen, 2004) allow researchers to more fully understand individual differences in change trajectories and may lead to fundamentally different understanding of change over time. The purpose of this paper is to provide a lay person's guide to LVGM in an effort to increase the use of these methods by counseling psychology researchers. In this paper, we discuss the differing conceptual frameworks from which conventional modeling techniques and LVGM techniques are drawn: variable-centered and person-centered frameworks, respectively. We next illustrate the assumptions and limitations of conventional analytic techniques and contrast these to the assumptions and limitations of LVGM. We then discuss three specific types of LVGM (latent class growth analysis, latent growth mixture modeling, and dual trajectory modeling), and provide a detailed example of latent class growth analysis using data from a longitudinal study of distress in recent sexual assault survivors. We conclude with suggestions for other areas of counseling psychology research that may benefit from the use of LVGM methods.
University of Minnesota Master of Arts thesis. March 2015. Major: Psychology. 1 computer file (PDF); vii, 40 pages, appendices A-B.
Identifying change trajectories using latent variable growth modeling: a primer.
Retrieved from the University of Minnesota Digital Conservancy,
Content distributed via the University of Minnesota's Digital Conservancy may be subject to additional license and use restrictions applied by the depositor.