Disentangling neighborhood effects in person-context research : an application of a neighborhood-based group decomposition

This paper proposes a framework to assess how compositional differences at the neighborhood level contribute to the moderating effect of neighborhood context on the association between individual risk-factors and delinquency. We propose a neighborhood-based group decomposition to partition person-context interactions into their constituent components. Using data from the National Longitudinal Study of Adolescent to Adult Health, we demonstrate the extent to which variation in the association between impulsivity and delinquency can be attributed to (1) differences in mean-levels of impulsivity and violence in disadvantaged neighborhoods and (2) differences in coefficients across neighborhoods. The moderating effect of neighborhood disadvantage can be attributed primarily to the stronger effect of impulsivity on violence in disadvantaged neighborhoods, while differences in average levels of violence and impulsivity account for 14 percent and 2 percent of the observed difference, respectively.