Impact of the Number of Response Categories on Linearity and Sensitivity of Self-Anchoring Scales
Abstract. In this research, the relationship between the number of response categories and the linearity and sensitivity of self-anchoring scales is tested. According to the functional measurement paradigm, people integrate their impressions of stimuli using simple algebraic models. Then the integrated stimulus is transformed into an overt response on a rating scale. The combination of a particular algebraic integration rule along with a linear rating scale predicts specific patterns in a factorial plot. In two functional measurement experiments we manipulated the number of categories of different self-anchoring scales and attempted to replicate a specific pattern based on the integration rules found in previous research. For both experiments, the predicted pattern was observed for all scales. This indicates that the number of response categories does not impact on the linearity of the scale. Moreover, there is no relationship between the number of response categories and the sensitivity of the scale as measured by the F ratio for the main effects.