An application of methods for clustered binary responses to a cardiovascular study with small sample size

Many clinicians have come to rely on the broad array of validity scales available on the MMPI and the MMPI-2. In this study, we evaluated the utility of 2 MMPI-2 validity scales, the K scale and VRIN scale, in a sample of 692 psychiatric inpatients. Specifically, the effects of the K-correction procedure and the exclusion of protocols based on VRIN scale elevations were examined on the relation between MMPI-2 basic clinical scales and external criteria including both self-report and clinician ratings of psychopathology. Results indicated that the K-correction procedure commonly used with the MMPI and MMPI-2 did not result in higher correlations with external criteria in comparison to non-K-corrected scores. In contrast, MMPI-2 protocols that produced VRIN T-score values > or = 80 generally produced lower correlations with patients self-reports and clinician ratings of psychopathology in comparison to protocols judged to be valid based on VRIN scale results.