Abstract
This study aimed to verify the effectiveness of the Likelihood Ratio Test (IRTLR) and the Multiple Indicators Multiple Causes (MIMIC) method in detecting differential item functioning (DIF) according to the percentage of items with DIF and ability distribution. To achieve the study's aim, nine ability distributions and three percentages of items with differential functioning were generated using the three-parameter model with the WINGEN program on 50 dichotomous items. The generated data were analyzed using the R program and the MULTILOG program. The results revealed statistically significant differences at α = 0.05 between Type I error and power means due to the percentage of items with DIF, DIF methods, and their interaction. Type I error increased with a higher percentage of items with DIF for both methods. The results also indicated that the power of the test decreased as the percentage of items with DIF increased. Furthermore, statistically significant differences at α = 0.05 were found due to ability distributions, DIF methods, and their interaction, with the MIMIC method being better at detecting DIF from ability distribution.
Recommended Citation
Qawaqneh, Ala'a and Bani Ata, Zaid
(2024)
"The Effectiveness of the Likelihood Ratio Test and Multiple Indicators Multiple Causes Method in Detecting Differential Item Functioning According to Sample Size, Percentage of Items with DIF, and Ability Distribution,"
Jordan Journal of Applied Science-Humanities Series: Vol. 40:
Iss.
2, Article 2.
Available at:
https://digitalcommons.aaru.edu.jo/jjoas-h/vol40/iss2/2