Accounting for Measurement Bias: A New Framework for Reliable Country Ranking in Large-Scale Educational Assessments

TL;DR

This paper introduces a new, efficient framework to correct measurement bias in large-scale educational assessments, improving the reliability of country rankings derived from IRT models.

Contribution

It presents a novel method that does not rely on anchor items or reference groups, ensuring more accurate and unbiased country performance rankings.

Findings

Corrected PISA 2022 country rankings across multiple domains.

Identified and analyzed measurement bias structures in large-scale assessments.

Provided theoretical guarantees for the method's ability to recover true rankings.

Abstract

International Large-scale Assessments (ILSAs), such as the Program for International Student Assessment (PISA) and the Trends in International Mathematics and Science Study (TIMSS), are cornerstone tools for global educational research and policy-making. By benchmarking educational quality and performance trends, these assessments enable countries to evaluate and share effective pedagogical structures. Specifically, ILSAs employ Item Response Theory (IRT) models to rank countries by students' performance on cognitive items. However, measurement bias--arising from linguistic, cultural, and curricular differences--poses a significant threat to the statistical inference of IRT models and, consequently, the validity of the resulting rankings. Neglecting this bias can lead to systematic errors in parameter estimation, ultimately distorting national standings. To address this, we propose a novel method that avoids the restrictive assumptions typical of existing approaches, such as the prior identification of unbiased anchor items or designated reference groups. Our approach is computationally efficient and provides theoretical guarantees for the reliable recovery of group rankings. We apply this method to PISA 2022 data across the mathematics, science, and reading domains, yielding corrected performance rankings and insights into the survey's measurement-bias structures.