Psychometric characteristics of the numerical ability test for Gulf students

Mohammed Al Ajmi, Siti Salina Mustakim, Samsilah Roslan, Rashid Almehrizi


This study investigates the psychometric properties of the numerical ability test using a three-parameter logistic (3PL) model within the framework of item response theory (IRT). The test comprises 30 dichotomous items and was administered to 2,689 fifth and sixth-grade students in schools across the Arab Gulf countries. The findings indicate a strong alignment of the test items with the three-parameter model, affirming the validity of the IRT approach. The test also meets the criteria for unidimensionality (UD) and local independence, establishing its psychometric soundness. Notably, the numerical ability test excels in discriminating between examinees with varying levels of numerical ability, particularly those with low or average abilities. Moreover, the scale exhibits a high level of reliability, with a marginal reliability coefficient of 0.83. These results suggest the potential for future research aimed at further enhancing the test’s precision and effectiveness.


Item response theory; Marginal reliability; Numerical ability; Psychometric characteristics; Three-parameter logistic model

Full Text:




  • There are currently no refbacks.

Copyright (c) 2024 Institute of Advanced Engineering and Science

International Journal of Evaluation and Research in Education (IJERE)
p-ISSN: 2252-8822, e-ISSN: 2620-5440
The journal is published by Institute of Advanced Engineering and Science (IAES) in collaboration with Intelektual Pustaka Media Utama (IPMU) 

View IJERE Stats

Creative Commons License
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.