, Volume 75, Issue 4, pp 581-612

A Two-Tier Full-Information Item Factor Analysis Model with Applications

Rent the article at a discount

Rent now

* Final gross prices may vary according to local VAT.

Get Access

Abstract

Motivated by Gibbons et al.’s (Appl. Psychol. Meas. 31:4–19, 2007) full-information maximum marginal likelihood item bifactor analysis for polytomous data, and Rijmen, Vansteelandt, and De Boeck’s (Psychometrika 73:167–182, 2008) work on constructing computationally efficient estimation algorithms for latent variable models, a two-tier item factor analysis model is developed in this research. The modeling framework subsumes standard multidimensional IRT models, bifactor IRT models, and testlet response theory models as special cases. Features of the model lead to a reduction in the dimensionality of the latent variable space, and consequently significant computational savings. An EM algorithm for full-information maximum marginal likelihood estimation is developed. Simulations and real data demonstrations confirm the accuracy and efficiency of the proposed methods. Three real data sets from a large-scale educational assessment, a longitudinal public health survey, and a scale development study measuring patient reported quality of life outcomes are analyzed as illustrations of the model’s broad range of applicability.

Part of this research is made possible by a pre-doctoral advanced quantitative methodology training grant (R305B080016) from the Institute of Education Sciences, a statistical methodology grant from the Institute of Education Sciences (R305D100039), and a grant from the National Institute on Drug Abuse (R01DA026943). The author is enormously grateful to Drs. Darren DeWalt, Susan Ennett, Robert Gibbons, Anthony Lehman, and David Thissen for their permission to use the data sets for numerical illustrations. Data collection for the Context project was supported by a grant from the National Institute on Drug Abuse (R01DA13459). The development of the Pediatric Asthma Impact Scale was funded by National Institute of Arthritis And Musculoskeletal and Skin Diseases (1U01AR052181-01). The development of IRTPRO was supported by the National Cancer Institute in the form of an SBIR contract (#HHSN-2612007-00013C) awarded to Scientific Software International. The views expressed in this paper are the author’s alone and do not reflect the views and policies of the funding agencies or grantees.