Forgoing Invariance Assumptions for Better Measurement in Comparative International Education Survey Research

• In Event: Alternative Ways of Estimating Performance in Large Scale Assessments

Abstract

In this theory project, we argue that forgoing measurement invariance assumptions to focus on optimal representation of participant attributes (e.g., students’ attitudes, educators’ perceptions) by the survey items in a comparative international education study may produce better measurement within countries, and more trustworthy comparisons of explanatory model results across countries.

Authors

• Anne Traynor, Purdue University

• Ming-Min Cheng, Purdue University

• Yimei Xiong, Purdue University