Contained in:
Book Chapter

The joint estimation of accuracy and speed: An application to the INVALSI data

  • Luca Bungaro
  • Marta Desimoni
  • Mariagiulia Matteucci
  • Stefania Mignani

In Italy, the National Institute for the Evaluation of the Education and Training System (INVALSI) every year administers standardized tests via computer-based testing (CBT) to students attending grades 8, 10, and 13. The CBT mode allows to collect data not only on the students’ response accuracy (RA) based on item responses, but also on their response times (RT). By using these data, it is now possible to estimate the speed ability of examinees, besides the usual ability (e.g. Italian language, mathematics or English ability). In this study, we use the 2018 mathematics data for grade 10 to estimate the ability and speed of students following the fully Bayesian approach of Fox et al. (2021), who implemented in the R package LNIRT the models of van der Linden (2007) and Klein Entik et al. (2009). In a second step, we use the estimated mathematics ability and speed in a bivariate multilevel model, where the first-level units are represented by students and the second-level units are represented by classes. Covariates such as gender, school type, immigrant status, economic, social, and cultural status, prior achievement, grade retention, student anxiety, class compositional variables, and geographical area are included in the model. The main results show that the ability and speed are inversely proportional, e.g. as ability increases, speed decreases. Also, differences in the students performance by gender and school type are significant for both ability and speed.

  • Keywords:
  • educational assessment,
  • large standardized test,
  • mathematics achievement,
  • IRT models for response times,
  • multilevel models,
+ Show More

Luca Bungaro

University of Bologna, Italy

Marta Desimoni

INVALSI, Italy - ORCID: 0000-0002-3407-0002

Mariagiulia Matteucci

University of Bologna, Italy - ORCID: 0000-0003-3404-6325

Stefania Mignani

University of Bologna, Italy - ORCID: 0000-0003-4746-1130

  1. Charlton, C., Rasbash, J., Browne, W.J., Healy, M., Cameron, B. (2020). MLwiN Version 3.05. Centre for Multilevel Modelling, University of Bristol.
  2. Fox, J. P., Klotzke, K., & Simsek, A. S. (2021). LNIRT: An R Package for Joint Modeling of Response Accuracy and Times. arXiv preprint arXiv:2106.10144.
  3. Klein Entink, R. H., Fox, J.-P., van der Linden, W. J. (2009). A Multivariate Multilevel Approach to the Modeling of Accuracy and Speed of Test Takers. Psychometrika, 74(1), pp. 21-48.
  4. Rasbash, J., Steele, F., Browne, W.J., Goldstein, H. (2017). A User's Guide to MLwiN, v3.00. Centre for Multilevel Modelling, University of Bristol.
  5. van der Linden, W. J. (2007). A Hierarchical Framework for Modeling Speed and Accuracy on Test Items. Psychometrika, 72(3), 287.
PDF
  • Publication Year: 2023
  • Pages: 221-226
  • Content License: CC BY 4.0
  • © 2023 Author(s)

XML
  • Publication Year: 2023
  • Content License: CC BY 4.0
  • © 2023 Author(s)

Chapter Information

Chapter Title

The joint estimation of accuracy and speed: An application to the INVALSI data

Authors

Luca Bungaro, Marta Desimoni, Mariagiulia Matteucci, Stefania Mignani

Language

English

DOI

10.36253/979-12-215-0106-3.39

Peer Reviewed

Publication Year

2023

Copyright Information

© 2023 Author(s)

Content License

CC BY 4.0

Metadata License

CC0 1.0

Bibliographic Information

Book Title

ASA 2022 Data-Driven Decision Making

Book Subtitle

Book of short papers

Editors

Enrico di Bella, Luigi Fabbris, Corrado Lagazio

Peer Reviewed

Publication Year

2023

Copyright Information

© 2023 Author(s)

Content License

CC BY 4.0

Metadata License

CC0 1.0

Publisher Name

Firenze University Press, Genova University Press

DOI

10.36253/979-12-215-0106-3

eISBN (pdf)

979-12-215-0106-3

eISBN (xml)

979-12-215-0107-0

Series Title

Proceedings e report

Series ISSN

2704-601X

Series E-ISSN

2704-5846

74

Fulltext
downloads

126

Views

Export Citation

1,339

Open Access Books

in the Catalogue

2,191

Book Chapters

3,709,757

Fulltext
downloads

4,396

Authors

from 923 Research Institutions

of 65 Nations

64

scientific boards

from 348 Research Institutions

of 43 Nations

1,246

Referees

from 379 Research Institutions

of 38 Nations