In this paper, we describe a new method we have developed for setting cut scores between levels of a test. We outline the wide variety of potential methods that have been used for such a process, and emphasize the need for a coherent conceptual framework under which the variety of methods could be understood. We then describe our particular…

Using the Rasch model for ordered categories, this paper provides a method for qualitative interpretations of data from an affective measure such as an attitude scale. This maximum information approach provides explicit qualitative information about the meaning of a score on the latent trait being assessed. (SLD)

Developed an empirical strategy for transforming ordinal counts and percentages to interval scale measures by recoding them as ordered categories and estimating Rasch model scale parameters. Demonstrated the strategy for a neighborhood construct defined by 8 characteristics of 77 Chicago, Illinois, neighborhoods. (SLD)

Studied whether the characteristics of the optimal categorization identified by Rasch analysis in a previous study could be maintained when the revised scale was applied to the same population (206 members of the original adult sample). Overall, the Rasch model fit well, and similar change patterns were observed in two category statistics provided…

Developed a measure of severity of mental retardation in adults, the Level of Activity in Profound/severe Mental Retardation, scale using Rasch analysis as a guide to item selection. Results from using the scale to rate 146 adults with mental retardation support the use of the scale for classification of severe and profound retardation. (SLD)

Suggests eight guidelines to aid the analyst in optimizing the manner in which rating scale categories cooperate to improve the usefulness of the resultant measures. Presents these guidelines in the context of Rasch analysis, but notes that they reflect aspects of rating scale functioning that impact all methods of analysis. (SLD)