Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Videos

Measuring student's proficiency in MOOCs: multiple attempts extensions for the Rasch model.

Dmitry Abbakumov1,2,3, Piet Desmet1,4, Wim Van den Noortgate1,2

  • 1ITEC imec, Leuven, Belgium.

Heliyon
|December 18, 2018
PubMed
Summary

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

"Robust" but Tiny: Methodological Influences and Inter-Individual (Un)Stability of the Serial Order Effect in Creativity.

Journal of Intelligence·2026
Same author

Six ways to handle dependent effect sizes in meta-analytic structural equation modeling: Is there a gold standard?

Research synthesis methods·2026
Same author

Mother-Adolescent Discrepancies in Reports of Relationship Quality and Early Adolescent Internalizing Symptoms.

Research on child and adolescent psychopathology·2026
Same author

Balancing stability and flexibility: investigating a dynamic <i>K</i> value approach for the Elo rating system in adaptive learning environments.

User modeling and user-adapted interaction·2025
Same author

Environmental sensitivity, supportive parenting, and the development of attachment and internalizing problems.

Development and psychopathology·2025
Same author

When Action Speaks Louder than Words: Exploring Non-Verbal and Paraverbal Features in Dyadic Collaborative VR.

Sensors (Basel, Switzerland)·2025

This study enhances student proficiency assessment in massive open online courses (MOOCs) by modeling multiple attempts and incorporating non-assessment data. The new approach improves prediction accuracy by 6% compared to traditional models.

Area of Science:

  • Educational Measurement
  • Psychometrics
  • Computer-Based Learning

Background:

  • Massive open online courses (MOOCs) present unique assessment challenges due to dynamic content, multiple attempts, and limited item pools.
  • Traditional psychometric models like Classical Test Theory (CTT) and Item Response Theory (IRT) struggle with these MOOC-specific assessment complexities.

Purpose of the Study:

  • To address the limitations of existing psychometric models in MOOCs.
  • To propose and validate advanced IRT models that account for assessment attempts and non-assessment data for improved student proficiency measurement.

Main Methods:

  • Developed cross-classification multilevel logistic extensions of the Rasch model.
  • Incorporated student attempt data and non-assessment data (video interaction, task engagement).
Keywords:
EducationPsychology

Related Experiment Videos

  • Validated the proposed models using logged data from one MOOC and cross-validation on three MOOCs.

    • Main Results:

    • Student performance changes across attempts vary individually and by item.
    • Student engagement with video lectures and practical tasks significantly predicts response correctness.
    • The proposed extended models achieved a 6% higher accuracy in predicting student item responses compared to the traditional Rasch model.

    Conclusions:

    • The developed psychometric extensions offer a significant improvement for MOOC assessment procedures.
    • These models provide a more accurate measure of student proficiency in the context of MOOCs.
    • The approach can serve as a valuable tool for educators and institutions evaluating student learning in online environments.