THE UNBIASED ANCHOR - BRIDGING THE GAP BETWEEN DIF AND ITEM BIAS

This research uses item response theory for the investigation of diffe rential item functioning (DIF) and examines the advantages of using a multivariate external criterion to match examinees from the various su bpopulations. An attempt was made to select a set of unbiased items to comprise the matching criterion. Expected course grades provided by t he students' teachers were examined and found to function similarly ac ross sex and race subgroups and were incorporated into the matching cr iterion. The inclusion of teachers' grades provides additional informa tion in the extreme proficiency ranges and has the potential to enhanc e the validity of subgroup comparisons and inferences of possible item bias. The use of an external matching criterion allows test developer s to embed the same short, designated anchor in multiple test forms, t hereby avoiding the circularity inherent to conventional DIF analyses and permitting comparison of DIF statistics across test forms.