Cracking the Code: A Framework for Ensuring Reliable TIMSS Test Scores for South African Learners


In many countries, including South Africa, the Trends in International Mathematics and Science Study (TIMSS) serves as a prominent assessment tool for evaluating students' achievements in mathematics and science. It's noteworthy, however, that the extent of the reliability of TIMSS test scores in South Africa has not been extensively investigated within the existing literature. This research employs generalizability theory to assess the reliability of 2019 TIMSS test scores among South African students. The primary objective is to gauge various forms of errors linked to test scores, encompassing factors such as tester and item effects. To achieve this, a single facet crossed design was adopted alongside a systematic sampling approach to gather item responses from 150 fourth-grade learners in response to 35 mathematics items drawn from an IEA IDB Analyzer Merge module. For data analysis, the gtheory package within the R language and statistical computing environment was employed. The assessment encompassed the computation of the generalizability (g) coefficient, the phi (Φ) coefficient, and the decision (d) study. The results divulged a g-coefficient of 0.989 and a Φ-coefficient of 0.981, indicating a notable level of reliability. These findings emphasize that TIMSS test scores remain unaffected by diverse sources of error, including those stemming from tester and item effects. This robust level of generalizability and reliability in the scores is thus validated. In the context of South Africa, these outcomes can potentially furnish policymakers and educators with more comprehensive insights for making informed decisions concerning the utilization and interpretation of TIMSS test scores.

Author Information
Musa Adekunle Ayanwale, University of Johannesburg, South Africa
Daniel Olutola Oyeniran, University of Alabama, United States
Joseph Taiwo Akinboboye, Federal University of Lafia, Nigeria

Paper Information
Conference: ECE2023
Stream: Assessment Theories & Methodologies

This paper is part of the ECE2023 Conference Proceedings (View)
Full Paper
View / Download the full paper in a new tab/window

To cite this article:
Ayanwale M., Oyeniran D., & Akinboboye J. (2023) Cracking the Code: A Framework for Ensuring Reliable TIMSS Test Scores for South African Learners ISSN: 2188-1162 The European Conference on Education 2023: Official Conference Proceedings
To link to this article:

Virtual Presentation

Comments & Feedback

Place a comment using your LinkedIn profile


Share on activity feed

Powered by WP LinkPress

Share this Research

Posted by James Alexander Gordon