Title: Introduction to Bayesian item response modelling

Authors: Jim Albert

Addresses: Department of Mathematics and Statistics, Bowling Green State University, Bowling Green, OH, USA

Abstract: This article provides a brief survey of developments in item response modelling from a Bayesian perspective. There is a description of the influential literature in the application of Markov chain Monte Carlo algorithms to fit IRT models. To give insight into current Bayesian work, we give overviews of recent papers on Bayesian multilevel modelling, IRT modelling using flexible asymmetric link functions, and detection of multidimensional structure using posterior predictive model checking. To show the recent advances in Bayesian software, we illustrate the use of an R package to fit a two-parameter IRT model by MCMC methods.

Keywords: MCMC methods; Markov chain Monte Carlo; posterior predictive checking; multilevel modelling; asymmetric link functions; Bayesian item response modelling; item response theory; IRT; psychometrics.

DOI: 10.1504/IJQRE.2015.071732

International Journal of Quantitative Research in Education, 2015 Vol.2 No.3/4, pp.178 - 193

Received: 19 Nov 2014
Accepted: 13 Jan 2015

Published online: 16 Sep 2015 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article