[Properties and benefits of applying the Rasch model in clinical diagnostics]

Abstract

In medical rehabilitation settings the use of appropriate assessment instruments is essential in many ways. A high quality of psychometric scales has to be ensured in order to allow for an appropriate interpretation of diagnostical data as well as for the evaluation of treatment outcomes and for quality assurance within rehabilitation clinics. Assessment scales developed by means of Rasch analysis possess desirable properties, especially because person parameters reach interval level by definition, and the assumption of only one latent dimension suffices to predict respondents behaviour sufficiently. Accordingly, Rasch scales are strictly one-dimensional and thus allow for unambiguous interpretation of diagnostic results. In this article it is shown which specific properties characterize Rasch scales and how Rasch analysis can be used in order to allow for a more differentiated and clinically meaningful data interpretation and to enhance analysis of clinical data.