Latent Transition Modeling of Progression of Health-Risk Behavior

Abstract

Longitudinal studies are helpful for understanding the complex progression of health-risk behavior over time and for identifying risk factors amenable to intervention. This article focusses on methods for modeling transitions between health-risk states over time when .are common multiple indicators of health-risk are available. Multiple measures of health-rick in studies which utilize questionnaires and surveys involving a series of self-report questions ach providing information regarding health-risk. A latent transition model is presented as am alternative to approaches that analyze indicators separately or use summative indices. These approaches ignore both the correlation between indicators and the multidimensional structure of health-risk. In the present article, transitions between latent health-risk states are modeled using a logistic regression model for nominal responses. A two-stage estimation procedure which is an estimating equations analogue of the pseudo-likelihood method is applied so that the complexity of full maximum likelihood is avoided and standard error calculation is straightforward. This procedure is applied to self-report data on weapons carrying behavior in an urban sample of schoolchildren followed annually for five years.