Appropriate Use of Test Scores from A Large-Scale Assessment

• In Event: Validity and Test Use

Abstract

This study examines consequences of model misfit and measurement error on reporting outcomes for a large-scale assessment. It investigates whether ignoring model misspecification and measurement error has any practical impact on reported scale scores for parents and teachers, also their secondary use in statistical analyses to inform policy makers.

Authors

• Salih Binici

• Yachen Luo, Human Resources Research Organization