jeehp Search


J Educ Eval Health Prof > Epub ahead of print
J Educ Eval Health Prof. 2018; 15: 7.
Published online March 24, 2018.
[Epub ahead of print]
Components of item selection algorithm in computerized adaptive testing
Kyung T. Han 
Graduate Management Admission Council, Reston, VA, USA
Correspondence  Kyung T. Han ,Email:
Editor:  Sun Huh, Hallym University, Korea
Submitted: March 8, 2018  Accepted after revision: March 24, 2018
Computerized adaptive testing (CAT) greatly improves measurement efficiency in high-stakes testing operations through the selection and administration of test items whose difficulty level is most relevant to each individual test taker. This paper explains the three components of a conventional CAT item selection algorithm—test content balancing, item selection criterion, and item exposure control. There were several noteworthy methodologies underlying each component. Test script method and constrained CAT method were for test content balancing. As for item selection criteria, there wereThe maximized Fisher information criterion, b-matching method, a-stratification method, weighted likelihood information criterion, efficiency balanced information criterion, and Kullback-Leibler information criterion.The randomesque method, Sympson-Hetter method, the unconditional and conditional multinomial methods, and the fade-away method were for item exposure control. Threre were several holistic approaches to CAT using the automated test assembly methods such as the shadow test approach and the weighted deviation model. Item usage and exposure count were variable according to the different item selection criteria and exposure control methods.. Finally, another important factors to consider when determining an appropriate CAT design are computer resources requirement, size of items, and the test length. . Logic of CAT is now being adopted in “adaptive learning,” which integrates the learning aspect and the (formative) assessment aspect of education into a continuous, individualized learning experience. Therefore, the algorithms and technologies in this review may be able to help medical health educators and high stakes test takers to adopt CAT more actively and efficiently.
Keywords: Algorithms; Computers; Computerized adaptive testing; Probability; Test Taking Skills
Share :
Facebook Twitter Linked In Google+
METRICS Graph View
  • 0 Crossref
  • 0 Scopus
  • 750 View
  • 19 Download

Editorial Office
Institute of Medical Education, College of Medicine, Hallym Unversity, Hallymdaehak-gil 1, Chuncheon 24252, Korea
TEL: +82-33-248-2652   FAX: +82-33-241-1672    

Copyright © 2018 by Korea Health Personnel Licensing Examination Institute. All rights reserved.

Developed in M2community

Close layer
prev next