Gender-Related Differential Validity and Differential Prediction in Interest Inventories

Following the suggestions of National Institute of Education and American Psychological Association Standards, this article addresses the issue of differential validity and differential prediction in the vocational interest domain as one major concern of test fairness. In order to investigate potential prediction bias in vocational interest measures, we first compare gender-specific validity coefficients for the prediction of person-environment fit and satisfaction to test for differential validity, and second, we examine gender differences in the slopes and intercepts of the regression model predicting person-environment fit to test for differential prediction. Results show evidence of differential validity and some indications of differential prediction in a standard Holland Interest Inventory. However, removing items showing large gender-specific differential item functioning, that is, controlling for measurement bias, slightly reduced prediction bias. Practical implications are discussed and further research objectives are suggested.