Poster #18 - Applying Unidimensional Models for Semi-Ordered Data to Scale Data With Neutral Responses

• In Event: 79.052 - MTCC Poster Session 19
  In Poster Session: 79.052-2 - Educational Measurement, Psychometrics, and Assessment Poster Session

Abstract

The purpose of this study is to evaluate a new modeling approach to calibrate unordered neutral responses in rating scale data. Unidimensional models for semiordered data within scale items (i.e., items with both ordered and nominal response categories) have recently been applied to rating scale data with “not applicable” response categories. This study explores whether these models could be used to incorporate unordered neutral responses into the latent trait estimation, and if so, how the method compares to alternate methods of dealing with neutral responses. Findings indicate these models can help practitioners evaluate the ordered or unordered nature of neutral responses and provide a viable alternative for theta estimation in the presence of an unordered neutral category.

Authors

• Sophie Cohn, University of Florida

• Anne Corinne Huggins-Manley, University of Florida