Novick meets Bayes
Improving the assessment of individual students in educational practice and research by capitalizing on assessors' prior beliefs
Publication date
2024-11-25
Document type
Forschungsartikel
Author
Organisational unit
Publisher
Sage Publications
Series or journal
Educational and Psychological Measurement
ISSN
Periodical volume
85
Periodical issue
3
First page
483
Last page
506
Peer-reviewed
✅
Part of the university bibliography
✅
Language
English
Abstract
The assessment of individual students is not only crucial in the school setting but also at the core of educational research. Although classical test theory focuses on maximizing insights from student responses, the Bayesian perspective incorporates the assessor’s prior belief, thereby enriching assessment with knowledge gained from previous interactions with the student or with similar students. We propose and illustrate a formal Bayesian approach that not only allows to form a stronger belief about a student’s competency but also offers a more accurate assessment than classical test theory. In addition, we propose a straightforward method for gauging prior beliefs using two specific items and point to the possibility to integrate additional information.
Version
Published version
Access right on openHSU
Metadata only access