Using Rasch measurement for instrument rating scale refinement

Our situation: Rasch measurement is an analysis tool that can provide validity evidence for instruments that attempt to measure student learning or other psychosocial behaviors, regardless if tools are newly created, modified, or previously developed. Rating scales are exceedingly common among psychosocial instruments and properly functioning rating scales are critical to effective measurement. Rasch measurement can help investigate this.

Methodological literature review: Aside from using Rasch measurement from the beginning to help create rigorous new measurement instruments, researchers can also benefit from employing Rasch measurement on previously developed instruments that had not included Rasch measurement during development. This article is focused on Rasch measurement's unique analysis of rating scales. That is, Rasch measurement can uniquely help examine if and how an instrument's rating scale is functioning among newly studied respondents (who will likely differ from the originally researched sample).

Our recommendations and their application: After reviewing this article, the reader should be able to describe Rasch measurement, including how it is focused on fundamental measurement and how it differs from classical test theory and item-response theory, and reflect on situations in their own research where a Rasch measurement analysis might be helpful for generating validation evidence with a previously developed instrument.

Potential impact: In the end, Rasch measurement can offer a helpful, unique, rigorous approach to further developing instruments that scientifically measure, accurately and precisely.