Evaluating mediation in longitudinal multivariate data: mediation effects for the Aban Aya Youth Project drug prevention program

Abstract

This study illustrates a method to evaluate mediational mechanisms in a longitudinal prevention trial, the Aban Aya Youth Project (AAYP). In previous studies, interventions of AAYP were found to be effective in reducing the growth of violence, substance use and unsafe sex among African American adolescents. In this article, we hypothesized that the effects of the interventions in reducing the growth of substance use behavior were achieved through their effects in changing intermediate processes such as behavioral intentions, attitudes toward the behavior, estimates of peers' behaviors, best friends' behaviors, and peer group pressure. In evaluating these mediational mechanisms, difficulties arise because the growth trajectories of the substance use outcome variable and some of the mediating variables were curvilinear. In addition, all of the multivariate mediational measures had planned missing data so that a score from the multiple items for a mediator could not be formed easily. In this article, we introduce a latent growth modeling (LGM) approach; namely, a two-domain LGM mediation model, in which the growth curves of the outcome and the mediator are simultaneously modeled and the mediation effects are evaluated. Results showed that the AAYP intervention effects on adolescent drug use were mediated by normative beliefs of prevalence estimates, friends' drug use behavior, perceived friends' encouragement to use, and attitudes toward the behavior.