Calls for papers

 

International Journal of Quantitative Research in Education

 

Special Issue on: "Bayesian Statistics in Psychometrics"

Guest Editor:
Yanyan Sheng, Southern Illinois University Carbondale, USA

Psychometric theories provide a framework to evaluate the psychometric properties of an instrument, such as item characteristics, test development, test-score equating, and differential function analysis. These theories rely on formulating a statistical model to specify the relationship among latent and observed variables while making certain assumptions about them.

The last two decades have seen an explosion in the popularity and use of Bayesian methods with psychometric models, largely as a result of the advances in sampling-based approaches to inference and the availability of enhanced computational technologies. Bayesian statistics, while using the prior belief to help derive the posterior distribution, offers an alternative perspective to probability and inference. It is well suited to address the increasingly complex phenomena and problems in educational and psychological measurement in that it can effectively tackle more complex and realistic models and problems, specifically as richer sources of data continue to be available. In this sense, the traditional frequentist methods are challenged.

In the last decade, much research has been conducted to employ Bayesian methods in developing and estimating modern psychometric models, such as factor analysis, structural equation modelling, item response theory, and latent class analysis. These studies demonstrated the advantages that Bayesian methods offer in psychometric modeling and call for continued efforts to develop new estimation approaches using Bayesian statistics while improving existing ones, and to carefully implement them in empirical problems that illustrate their practical appeal.

This special issue focuses on highlighting the application of Bayesian methods to empirical problems in educational and psychological measurement. Researchers are especially welcome to submit articles that address empirical research that (1) describes Bayesian estimation and inference with a psychometric model, or (2) features the advantage of Bayesian methods over the frequentist approach.

Subject Coverage
Suitable topics include the following:

• Estimation techniques and simulation, computation
• Markov chain Monte Carlo (MCMC) simulation techniques
• Parallel computing
• Development of new psychometric models
• Item response theory
• Structural equation modeling
• Generalisability theory
• Multilevel models
• Missing data analysis
• Nonparametric and semiparametric models
• Applications of Bayesian modelling in psychometrics
• Model comparison and model evaluation

The above list is not exclusive; other contributions on relevant topics will also be considered. This project aims at developing a comprehensive understanding of the topic through case studies on good or bad practices.

Notes for Prospective Authors

Submitted papers should not have been previously published nor be currently under consideration for publication elsewhere. (N.B. Conference papers may only be submitted if the paper has been completely re-written and if appropriate written permissions have been obtained from any copyright holders of the original paper).

All papers are refereed through a peer review process.

All papers must be submitted online. To submit a paper, please read our Submitting articles page.

Important Dates

Manuscripts due by: 30 October, 2014

Notification to authors: 30 December, 2014

Final versions due by: 28 February, 2015