Cognitive Diagnosis Modeling Incorporating Response Times and Fixation Counts: Providing Comprehensive Feedback and Accurate Diagnosis

Peida Zhan*, Kaiwen Man*, Stefanie A. Wind and Jonathan Malone
Additional contact information
Peida Zhan*: Zhejiang Normal University
Stefanie A. Wind: University of Alabama
Jonathan Malone: University of Maryland

Journal of Educational and Behavioral Statistics, 2022, vol. 47, issue 6, 736-776

Abstract: Respondents’ problem-solving behaviors comprise behaviors that represent complicated cognitive processes that are frequently systematically tied to one another. Biometric data, such as visual fixation counts (FCs), which are an important eye-tracking indicator, can be combined with other types of variables that reflect different aspects of problem-solving behavior to quantify variability in problem-solving behavior. To provide comprehensive feedback and accurate diagnosis when using such multimodal data, the present study proposes a multimodal joint cognitive diagnosis model that accounts for latent attributes, latent ability, processing speed, and visual engagement by simultaneously modeling response accuracy (RA), response times, and FCs. We used two simulation studies to test the feasibility of the proposed model. Findings mainly suggest that the parameters of the proposed model can be well recovered and that modeling FCs, in addition to RA and response times, could increase the comprehensiveness of feedback on problem-solving-related cognitive characteristics as well as the accuracy of knowledge structure diagnosis. An empirical example is used to demonstrate the applicability and benefits of the proposed model. We discuss the implications of our findings as they relate to research and practice.

Keywords: cognitive diagnosis; eye tracking; response times; fixation counts; process data; biometric data; problem-solving (search for similar items in EconPapers)
Date: 2022
References: Add references at CitEc
Citations:

Downloads: (external link)
https://journals.sagepub.com/doi/10.3102/10769986221111085 (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:47:y:2022:i:6:p:736-776

DOI: 10.3102/10769986221111085

Access Statistics for this article

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