Suchergebnisse

The Contrived Respondent Technique is introduced as an addition to methods for improving the reproducibility of Guttmantype scales by operations performed after the final set of data has been gathered. The rationale of the H-technique is applied to R's instead of items with comparable efficiency in improving reproducibility. Sacrificing the unique responses of individuals rather than unique responses to items is possible because the cumulative scaling model makes no formal distinction between S's & items in the S-by-item response matrix. This technique may be used instead of or in addition to existing methods whenever att's are used as dependent variables, characterizing categories of persons rather than single individuals. AA.