What the study found
The study found that a formative adaptive assessment framework for engineering education can provide competency-oriented feedback, learning monitoring, and instructional interpretation. It also showed high estimation accuracy and satisfactory reliability for formative use across most learner profiles.
Why the authors say this matters
The authors conclude that adaptive assessment can be a pedagogically grounded tool for formative learning support, instructional decision-making, and quality assurance in engineering education. They frame this as important because assessment in this setting should support learning regulation and educational quality, not only measurement efficiency.
What the researchers tested
The researchers proposed and evaluated a formative adaptive assessment framework that combines an item response theory (IRT) computer-adaptive testing engine with a Bayesian network diagnostic component. The framework used dichotomous multiple-choice items aligned with engineering learning outcomes, with item calibration based on data from 612 university students in computer science and a simulation study involving 500 simulated learners.
What worked and what didn't
The results showed high estimation accuracy, with r = 0.912, and satisfactory reliability for formative use across most learner profiles. Reduced precision at the extremes of the proficiency continuum and imbalances in item exposure were also observed.
What to keep in mind
The abstract says the main structural limits were tied to item bank coverage and curriculum representation rather than to the adaptive algorithms themselves. No other limitations are described in the available summary.
Key points
- The framework combined IRT-based computer-adaptive testing with Bayesian network diagnostic modelling.
- The study reported high estimation accuracy, with r = 0.912.
- Reliability was described as satisfactory for formative use across most learner profiles.
- Reduced precision appeared at the extremes of the proficiency continuum.
- Item exposure was imbalanced, mainly because of item bank coverage and curriculum representation.
Disclosure
- Research title:
- Adaptive formative assessment showed high estimation accuracy
- Authors:
- Mohamed El Msayer, Bouchra Bouihi, Abdelmajid Bousselham, Essaadia Aoula, Adel Deraoui
- Institutions:
- Laboratoire de Recherche Scientifique, Université Hassan II Mohammedia, Université Hassan II Mohammedia, Université Hassan II Mohammedia, Université Hassan II Mohammedia, University of Hassan II Casablanca, University of Hassan II Casablanca, University of Hassan II Casablanca, University of Hassan II Casablanca
- Publication date:
- 2026-03-03
- OpenAlex record:
- View
Get the weekly research newsletter
Stay current with scholarly research without reading academic papers — one filtered digest, every Friday.