Analysis of Differential Item Functioning in Comparative Education Studies: the Case of the Civic Education Studies

This study proposes and illustrates a two-stage strategy to analyze differential item functioning in comparative educational studies. At the first stage, within each country, item difficulties are estimated. At the second stage, results are combined across countries using a meta-analytic framework to investigate (a) whether the items function consistently at the country level, and (b) what country characteristics predict item difficulties. To illustrate, we analyzed data on student responses to 13 civic skills items from 28 countries, collected under the Civic Education Study of the International Association for the Evaluation of Educational Achievement (IEA), and reported initial findings. Implications of this strategy for comparative educational studies are discussed.