MCMC estimation of multidimensional IRT models

Anton Beguin, Cornelis A.W. Glas

Research output: Book/ReportReportProfessional

65 Downloads (Pure)

Abstract

A Bayesian procedure to estimate the three-parameter normal ogive model and a generalization to a model with multidimensional ability parameters are discussed. The procedure is a generalization of a procedure by J. Albert (1992) for estimating the two-parameter normal ogive model. The procedure will support multiple samples from multiple populations and restrictions on the factor matrix for testing specific hypotheses about the ability structure. The technique is illustrated using simulated and real data. A Markov chain Monte Carlo (MCMC) procedure is used to sample the posterior distributions of interest and needed chains are constructed using the Gibbs sampler (A. Gelfand and A. Smith, 1990).
Original languageEnglish
Place of PublicationEnschede
PublisherUniversity of Twente, Faculty Educational Science and Technology
Publication statusPublished - 1998

Publication series

NameOMD Reseach Report
PublisherUniversity of Twente, Faculty of Educational Science and Technology
No.98-14

Keywords

  • Simulation
  • Estimation (Mathematics)
  • Item Response Theory
  • Bayesian Statistics
  • IR-103766
  • Markov Processes
  • Monte Carlo Methods
  • METIS-136530
  • Ability

Fingerprint Dive into the research topics of 'MCMC estimation of multidimensional IRT models'. Together they form a unique fingerprint.

  • Cite this

    Beguin, A., & Glas, C. A. W. (1998). MCMC estimation of multidimensional IRT models. (OMD Reseach Report; No. 98-14). Enschede: University of Twente, Faculty Educational Science and Technology.