Methodological difficulties of modeling peer influence

Using data from wave IV of the National Youth Survey, the effect of drug-related peer delinquency on delinquency is modeled as a function of the bond to peers. Due to the complexities of such a test, this article discusses limitations of both the standard linear model and Tobit regression when applied to delinquency data coupled with statistical interactions. Results from a censored least absolute deviations (CLAD) model and why this is a useful alternative to OLS and Tobit are discussed. The results suggest the effect of peers increases with the intensity of bonds to peers. However, encouragement is provided for further investigating peer influence, a process, as opposed to an additive peer effect.