Using cut-off scores in screening tests is an economical way to identify disorders in individuals. Two case-control studies were conducted among healthy and inpatient psychotherapy samples. Patients were suffering from depressive disorders. In the first study (N = 296) we used a German short form of the Center for Epidemiologic Studies-Depression Scale (CES-D) for screening purposes. In the second study (N = 154) we used the trait scale of the State-Trait Depression Scales (STDS-T). Based on Rasch model analyses, the item-person maps showed that both instruments are suitable to assess depressive mood in healthy and patient samples. Analyses of the areas under the receiver-operating characteristic curves revealed a high diagnostic power of both instruments. Several cut-off scores were evaluated regarding sensitivity, specificity, and Youden-criterion. Following the Youden-criterion, the optimal cut-off scores for diagnosing depressive disorders were ≥ 18 for the CES-D and ≥ 25 for the STDS-T. The analyses provide empirical evidence for clinical decision-making.