The Validity of a Self-reported Delinquency Scale

Abstract

Self-reported delinquency scales have been widely adopted by researchers seeking to measure delinquency. Establishing the validity of these scales is critical because if valid measures are not created, findings about the correlates of delinquency will be of limited use in testing theory and formulating public policy. In this article, the authors use data from the first wave of the National Youth Survey to examine the measurement properties of a commonly used delinquency scale. The authors use the Rasch measurement model to test whether the scale meets the requirements of fundamental measurement and whether consistent measurement has occurred across subgroups including gender, age, race, and place of residence. Our results indicate that the original response category options are inadequate and differential item functioning exists across various subgroups. Methodological implications and directions for future research are identified.