Abstract
PURPOSE: To present mixture regression analysis as an alternative to more standard regression analysis for predicting adolescent delinquency. We demonstrate how mixture regression analysis allows for the identification of population subgroups defined by the salience of multiple risk factors. METHODS: We identified population subgroups (i.e., latent classes) of individuals based on their coefficients in a regression model predicting adolescent delinquency from eight previously established risk indices drawn from the community, school, family, peer, and individual levels. The study included N = 37,763 10th-grade adolescents who participated in the Communities That Care Youth Survey. Standard, zero-inflated, and mixture Poisson and negative binomial regression models were considered. RESULTS: Standard and mixture negative binomial regression models were selected as optimal. The five-class regression model was interpreted based on the class-specific regression coefficients, indicating that risk factors had varying salience across classes of adolescents. CONCLUSIONS: Standard regression showed that all risk factors were significantly associated with delinquency. Mixture regression provided more nuanced information, suggesting a unique set of risk factors that were salient for different subgroups of adolescents. Implications for the design of subgroup-specific interventions are discussed.