Demonstrating the Difference between Classical Test Theory and Item Response Theory Using Empirical Data: Implication for Educational Research

Abstract

The study demonstrated by determining among others the reliability; mean score difference between male and female candidates in 2019/2020 Katsina State BECE in mathematics scores/items using CTT and IRT. Expose facto design was used for the study. The population of the study consisted of 65,797 (42,110 male and 23,687 female) candidates. A multi-stage stratified random sampling technique was used to select 500(290 male and 210 female) candidates. Data for the study was obtained from the KSERC Examination Officer. Hypotheses were tested at \(\alpha\) = 0.05 level of significance. The data were analyzed using SPSS and WINSTEPS version 4.8.2.0 software. Some of the findings from the study revealed a reliability coefficient of 0.99 using both CCT and IRT; it is a statistically significant (t = 5.663, df = 449, p = 0.000) difference between the mean score of male and female candidates; and 57% (34) of the BECE Items in Mathematics have different difficulty levels for male and female candidates. Implications from the findings for educational research were also discussed. A similar study in a different field to determine the possibility or otherwise of combined CTT and IRT analysis was the recommendation made from the study.