Assessment of Multiple-Form Structure Designs of Multistage Testing Using Item Response Theory

• In Event: Hilton Roundtable Session 4
  In Roundtable Session: Division D Section 1 Roundtable Topic: Applications of Item Response Theory

Abstract

This study assessed multiple-form structure designs of multistage testing (MST)as an alternative to classical linear testing (CLT) using the same items. Eight MST conditions were assessed for each section of the General-Aptitude-Test (GAT) with varied assembly methods, routing methods, and panel structures. Findings revealed trivial differences in the estimated ability and standard error means among all conditions, but the correlations with CLT score were affected. For testing practitioners, the difference between MST conditions is of little concern and what is a concern involves the test’s purpose. If the test aims to estimate examinee ability regardless of classification, the combination of the Narrow-range (NR) and Approximate-Maximum-Information method in MST-2Stage while the NR with Defined-Population-Intervals performed better for classification.

Authors

• Hanan M. AlGhamdi, National Center for Assessment

• Kathy E. Green, University of Denver