No abstract

To explore the co-evolution of friendship tie choice and alcohol use behavior among 1,284 adolescents from 12 small schools and 976 adolescents from one big school sampled in the National Longitudinal Study of Adolescent to Adult Health (AddHealth), we apply a Stochastic Actor-Based (SAB) approach implemented in the R-based Simulation Investigation for Empirical Network Analysis (RSiena) package. Our results indicate the salience of both peer selection and peer influence effects for friendship tie choice and adolescent drinking behavior. Concurrently, the main effect models indicate that parental monitoring and the parental home drinking environment affected adolescent alcohol use in the small school sample, and that parental home drinking environment affected adolescent drinking in the large school sample. In the small school sample, we detect an interaction between the parental home drinking environment and choosing friends that drink as they multiplicatively affect friendship tie choice. Our findings suggest that future research should investigate the synergistic effects of both peer and parental influences for adolescent friendship tie choices and drinking behavior. And given the tendency of adolescents to form ties with their friends' friends, and the evidence of local hierarchy in these networks, popular youth who do not drink may be uniquely positioned and uniquely salient as the highest rank of the hierarchy to cause anti-drinking peer influences to diffuse down the social hierarchy to less popular youth. As such, future interventions should harness prosocial peer influences simultaneously with strategies to increase parental support and monitoring among parents to promote affiliation with prosocial peers.

Recent developments have made model-based imputation of network data feasible in principle, but the extant literature provides few practical examples of its use. In this paper we consider 14 schools from the widely used In-School Survey of Add Health (Harris et al., 2009), applying an ERGM-based estimation and simulation approach to impute the network missing data for each school. Add Health's complex study design leads to multiple types of missingness, and we introduce practical techniques for handing each. We also develop a cross-validation based method – Held-Out Predictive Evaluation (HOPE) – for assessing this approach. Our results suggest that ERGM-based imputation of edge variables is a viable approach to the analysis of complex studies such as Add Health, provided that care is used in understanding and accounting for the study design.

This study uses National Longitudinal Study of Adolescent Health (Add Health) data to explore the co-evolution of friendship networks and delinquent behaviors. Using a stochastic actor-based (SAB) model, we simultaneously estimate the network structure, influence process, and selection process on adolescents in 12 small schools (N = 1,284) and 1 large school (N = 976) over three time periods. Our results indicate the presence of both selection and influence processes. Moderating effects were tested for density, centrality, and popularity, with only a weak interaction effect for density and influence in the small schools (p < .10). Contexts outside the school affected school networks: adolescents in the large school were particularly likely to form ties to others from equally disadvantaged neighborhoods, and adolescents in the small schools with more outside of school ties increased their delinquency over time. These findings support the importance of delinquency in peer selection and influence processes.