Computerized Adaptive Testing Using a Class of High-Order Item Response Theory Models

Hung Yu Huang, Po-Hsi Chen, Wen Chung Wang

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

In the human sciences, a common assumption is that latent traits have a hierarchical structure. Higher order item response theory models have been developed to account for this hierarchy. In this study, computerized adaptive testing (CAT) algorithms based on these kinds of models were implemented, and their performance under a variety of situations was examined using simulations. The results showed that the CAT algorithms were very effective. The progressive method for item selection, the Sympson and Hetter method with online and freeze procedure for item exposure control, and the multinomial model for content balancing can simultaneously maintain good measurement precision, item exposure control, content balance, test security, and pool usage.

Original languageEnglish
Pages (from-to)689-706
Number of pages18
JournalApplied Psychological Measurement
Volume36
Issue number8
DOIs
Publication statusPublished - 2012 Nov 1

Fingerprint

model theory
human sciences
simulation
performance

Keywords

  • computerized adaptive testing
  • higher order
  • item exposure control
  • item response theory
  • test security

ASJC Scopus subject areas

  • Social Sciences (miscellaneous)
  • Psychology (miscellaneous)

Cite this

Computerized Adaptive Testing Using a Class of High-Order Item Response Theory Models. / Huang, Hung Yu; Chen, Po-Hsi; Wang, Wen Chung.

In: Applied Psychological Measurement, Vol. 36, No. 8, 01.11.2012, p. 689-706.

Research output: Contribution to journalArticle

@article{3a6da4627bf649feaf4be6e4cadf0bd9,
title = "Computerized Adaptive Testing Using a Class of High-Order Item Response Theory Models",
abstract = "In the human sciences, a common assumption is that latent traits have a hierarchical structure. Higher order item response theory models have been developed to account for this hierarchy. In this study, computerized adaptive testing (CAT) algorithms based on these kinds of models were implemented, and their performance under a variety of situations was examined using simulations. The results showed that the CAT algorithms were very effective. The progressive method for item selection, the Sympson and Hetter method with online and freeze procedure for item exposure control, and the multinomial model for content balancing can simultaneously maintain good measurement precision, item exposure control, content balance, test security, and pool usage.",
keywords = "computerized adaptive testing, higher order, item exposure control, item response theory, test security",
author = "Huang, {Hung Yu} and Po-Hsi Chen and Wang, {Wen Chung}",
year = "2012",
month = "11",
day = "1",
doi = "10.1177/0146621612459552",
language = "English",
volume = "36",
pages = "689--706",
journal = "Applied Psychological Measurement",
issn = "0146-6216",
publisher = "SAGE Publications Inc.",
number = "8",

}

TY - JOUR

T1 - Computerized Adaptive Testing Using a Class of High-Order Item Response Theory Models

AU - Huang, Hung Yu

AU - Chen, Po-Hsi

AU - Wang, Wen Chung

PY - 2012/11/1

Y1 - 2012/11/1

N2 - In the human sciences, a common assumption is that latent traits have a hierarchical structure. Higher order item response theory models have been developed to account for this hierarchy. In this study, computerized adaptive testing (CAT) algorithms based on these kinds of models were implemented, and their performance under a variety of situations was examined using simulations. The results showed that the CAT algorithms were very effective. The progressive method for item selection, the Sympson and Hetter method with online and freeze procedure for item exposure control, and the multinomial model for content balancing can simultaneously maintain good measurement precision, item exposure control, content balance, test security, and pool usage.

AB - In the human sciences, a common assumption is that latent traits have a hierarchical structure. Higher order item response theory models have been developed to account for this hierarchy. In this study, computerized adaptive testing (CAT) algorithms based on these kinds of models were implemented, and their performance under a variety of situations was examined using simulations. The results showed that the CAT algorithms were very effective. The progressive method for item selection, the Sympson and Hetter method with online and freeze procedure for item exposure control, and the multinomial model for content balancing can simultaneously maintain good measurement precision, item exposure control, content balance, test security, and pool usage.

KW - computerized adaptive testing

KW - higher order

KW - item exposure control

KW - item response theory

KW - test security

UR - http://www.scopus.com/inward/record.url?scp=84867342499&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84867342499&partnerID=8YFLogxK

U2 - 10.1177/0146621612459552

DO - 10.1177/0146621612459552

M3 - Article

VL - 36

SP - 689

EP - 706

JO - Applied Psychological Measurement

JF - Applied Psychological Measurement

SN - 0146-6216

IS - 8

ER -