Usability of Psychometric Admeasurements

Dr. J. M. Müller, Psychological Institute of Tübingen

Friedrichstrasse 21, 72072 Tübingen

 

Abstract:

Test users too often neglect the psychometric properties of a test as indicators of several aspects of quality (Archer, Maruish, Imhof & Piotrowski, 1991; Piotrowski & Keller, 1992; Wade & Baker, 1977). This may also hold in computer-based testing. For this reason, a theory-based analysis of the weakness of psychometric coefficients is recommended. A list of about 20 criteria for evaluating the usability of psychometric admeasurements with respect to the foundation, scale and interpretation of a coefficient is presented. Based on these criteria, several coefficients of reliability are evaluated. Because of certain weaknesses of these coefficients,  alternatives are proposed, especially a coefficient for displaying the performance on separate test scores ‘Personenunterscheidungsvermögen’ (Müller, 2001) and a rescaled reliability coefficient (‘Differenziertheit’, Müller, 2001).  Both coefficients are introduced and discussed. Additionally, SAS-Marcos to calculate the coefficients are given.

Archer, R. P., Maruish, M., Imhof, E. A. & Piotrowski, C. (1991). Psychological test usage with adolescent clients: 1990 survey findings. Professional Psychology: Research and Practice, 22, 247-252.

Müller, J. M. (2001). Kennwerte psychologischer Testverfahren. Dissertation. http://elib.suub.uni-bremen.de/publications/dissertations/E-Diss165_M%FCller.pdf

Piotrowski, C. & Keller, J. W. (1992). Psychological testing in applied settings: A literature review from 1982-1992. Journal of Training & Practice in Professional Psychology, 6, 74-82.

Wade, T. C. & Baker, T. B. (1977). Opinions and use of psychological test. American Psychologist, 32, 874-882.

 

Keywords: error of measurement, usability, test selection, diagnostic, reliability.