Validation of diagnostic measures based on latent class analysis: A step forward in response bias research.

Abstract

The use of criterion group validation is hindered by the difficulty of classifying individuals on latent constructs. Latent class analysis (LCA) is a method that can be used for determining the validity of scales meant to assess latent constructs without such a priori classifications. The authors used this method to examine the ability of the L scale of the MMPI-2 (J. N. Butcher et al., 2001), the Impression Management scale of the Balanced Inventory of Desirable Responding (D. L. Paulhus, 1991), and the Endorsement of Excessive Virtue scale of the Psychological Screening Inventory (R. I. Lanyon, 1970) to identify favorable response bias (misrepresentation) in a situation where no criterion for individual classifications existed. Results suggest that LCA can be used as a method for assessing the validity of scales that measure unobservable conditions.