The purpose of this research is to contribute evidence regarding the c
onstruct validity of a three-item locus-of-control measure specific to
crime victimization. The scale was used to determine whether specific
populations were more likely than others to agree with one of the ori
entations to control suggested by Levenson, these being internal, powe
rful others, and chance. The latter two dimensions represent distinct
types of external orientations. The analysis was based on results from
a telephone survey of a randomly selected sample of 666 residents, ag
ed 18 years of older, of a midwestern city. Logistic regression using
continuation logits yielded results consistent in general with expecta
tions derived from the literature, but several interaction effects inv
olving demographic and crime-specific variables were apparent.