Bayesian Item Selection Criteria for Adaptive Testing

1998/06/01 by Wim J. van der Linden · 1 citation
Decision Sciences · Computer Science · Social Sciences · #Psychometric Methodologies and Testing #Advanced Statistical Modeling Techniques #Educational Assessment and Pedagogy

paper · pdf · doi:10.1007/bf02294775

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.

Citations

• Weighted Likelihood Estimation of Ability in Item Response Theory

Cited by

• Laplace-PSN-IRT: Uncertainty Quantification for Neural Item Response Theory Models of LLM Benchmarks

Related

• Bayesian information theoretic model-averaging stochastic item selection for computer adaptive testing
• On the Consistency of Bayesian Adaptive Testing under the Rasch Model
• Probabilistic Models for Computerized Adaptive Testing: Experiments
• A Comparison of Item‐Selection Methods for Adaptive Tests with Content Constraints
• Probabilistic Models for Computerized Adaptive Testing