Testing control theory and differential association: A reananlysis of the Richmond Youth Project Data

In what has become a classic work in the field Matsueda (1982) tested control theory against differential association theory using Hirschi's (1969) Richmond Youth Project data. Matsueda found that measures of "definitions favorable to law violation" entirely mediated the effect of his social control measures and friends' delinquency, and concluded that differential association theory was supported over control theory. We note several problems with Matsueda's specification of control theory, and we reanalyze the Richmond data including measures of commitment to conventional goals and several attachment to parents variables that Matsueda excluded. We also propose and test a new method of measuring the social bond, conceptualizing the social bond as a second-order latent construct. In contrast with Matsueda's findings, we find that the social bond and friends' delinquency retain important direct effects on delinquency, and that these effects are greater than those of definitions. Thus, our results are more supportive of control theory than differential association theory.