Affordable Access

Access to the full text

Bayesian item selection criteria for adaptive testing

Authors
  • van der Linden, Wim J.1
  • 1 University of Twente, Department of Educational Measurement and Data Analysis, Enschede, 7500 AE, The Netherlands , Enschede
Type
Published Article
Journal
Psychometrika
Publisher
Springer-Verlag
Publication Date
Jun 01, 1998
Volume
63
Issue
2
Pages
201–216
Identifiers
DOI: 10.1007/BF02294775
Source
Springer Nature
Keywords
License
Yellow

Abstract

Owen (1975) proposed an approximate empirical Bayes procedure for item selection in computerized adaptive testing (CAT). The procedure replaces the true posterior by a normal approximation with closed-form expressions for its first two moments. This approximation was necessary to minimize the computational complexity involved in a fully Bayesian approach but is no longer necessary given the computational power currently available for adaptive testing. This paper suggests several item selection criteria for adaptive testing which are all based on the use of the true posterior. Some of the statistical properties of the ability estimator produced by these criteria are discussed and empirically characterized.

Report this publication

Statistics

Seen <100 times