Detecting Compromised Items With Response Times Using a Bayesian Change-Point Approach

Yang Du and Susu Zhang
Additional contact information
Yang Du: Nvidia Corp
Susu Zhang: University of Illinois Urbana-Champaign

Journal of Educational and Behavioral Statistics, 2025, vol. 50, issue 2, 296-330

Abstract: Item compromise has long posed challenges in educational measurement, jeopardizing both test validity and test security of continuous tests. Detecting compromised items is therefore crucial to address this concern. The present literature on compromised item detection reveals two notable gaps: First, the majority of existing methods are based upon a non-Bayesian framework; second, many of these approaches exclusively rely on examinees’ responses for detection, neglecting valuable data such as response times. In this study, we propose a Bayesian change-point method that integrates both responses and response times to detect compromised items in continuous tests. This two-phase approach is designed for iterative use. The accuracy and efficiency of the proposed method are assessed in three simulations and an operational data example. The results demonstrate the method’s effectiveness in accurately and efficiently detecting compromised items. Additionally, the incorporation of response times significantly enhances both detection accuracy and efficiency.

Keywords: test security; computerized tests; item compromise; Bayesian change-point detection; Shiryaev procedure (search for similar items in EconPapers)
Date: 2025
References: Add references at CitEc
Citations:

Downloads: (external link)
https://journals.sagepub.com/doi/10.3102/10769986241290713 (text/html)

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:sae:jedbes:v:50:y:2025:i:2:p:296-330

DOI: 10.3102/10769986241290713

Access Statistics for this article

More articles in Journal of Educational and Behavioral Statistics
Bibliographic data for series maintained by SAGE Publications ().