Criterion Measures Are Not Always Continuous: Consequential Validity Ratio for Logistic Regression

• In Event: Enhancing Validity and Reliability in Educational Measurement and Assessments

Abstract

With the evolution of social values, validity evidence based on testing consequences has received greater attention in measurement research and practice. The Consequential Validity Ratio (CVR) is a recently developed method for quantifying and representing how well test scores avoid the improper influence of participant demographics in the prediction of a validation criterion. The original CVR can only be used with the continuous criterion variables; however, binary criteria are also common in scale validation practice. This study theoretically proposes six candidate formulas for the CVR that can be used with binary criteria in a logistic regression framework (i.e., CVRB), and a simulation analysis was conducted to help determine its final formulation. Two empirical examples were provided to illustrate this index.

Authors

• Yixiao Dong, University of California - Santa Barbara

• Kushmakar Baral, University of Denver

• Denis Dumas, University of Georgia