The Effect of the Difference in the Response Model of the Item (1PL, 2PL, 3PL) on the Differential Item Functioning
DOI:
https://doi.org/10.36473/ujhss.v62i1.1964Abstract
The study aimed to examine the effect of choosing the item response model (One- Parameter, Two-Parameters, Three-Parameters) in revealing the Differential Item Functioning and comparison percentage of item with Differential Item Functioning and knowing the significance of the differences in the value of the Differential Item Functioning and its mean. To achieve the objectives of the study, the researcher relied on the results of the master’s enrollment test held at the Higher Institute of Languages at the University of Aleppo, which consisted of (60) items of the objective type, dual response (0 or 1), and their response to (1000) applicants from theoretical and applied colleges. After making sure that the assumptions of the response theory of the one-dimensional singularity (using factor analysis, item saturation, double-correlation coefficient), local independence and characteristic curve of singularity, the researcher made sure of the suitability of the vocabulary for the two-dimensional models using Jmetrik, the results showed: 1. That (31.481%) of the items did not show a differential DIF according to the characteristic curve method of the paragraph in the case of the three models (1PL, 2PL, 3PL). 2. That (44.444%) of the items showed DIF according to the characteristic curve method for the item when only one model (1PL, 2PL, 3PL). 3. That (24.074%) of the items showed a DIF according to the item characteristic curve method in two models. 4. No item showed DIF according to the item characteristic curve method in all models. 5. The results showed that the individual characteristic curve method for detecting DIF of the two-parameter model showed the highest percentage of items with DIF with a percentage of (68.5%), and then the percentage of items with DIF according to the characteristic curve method for the item and the one-parameter model with a percentage of (22.222%). and then the percentage of items with DIF according to the characteristic curve method for the ITEMS and the three-parameter model at a rate of (1.9%). 6.
Downloads
References
Allam, Saladin. (2007). Diagnostic tests, reference criterion: in the educational, psychological and training fields, Cairo: Dar Al-Fikr Al-Arabi.
Alnaji, Adel. (2011) The effectiveness of the constrained factor analysis method compared to several methods for detecting the differential performance on the individual. Unpublished doctoral thesis. Yarmouk University.
Al-Sakarna, Muhammad Nour. (2017). Detection of the differential performance of the items of a trend scale according to the distribution of negative items, the method of detection and the level of significance. Unpublished Ph.D. thesis. Yarmouk University: Jordan.
Angoff, W. H. (1993). Perspectives on differential item functioning methodology.
Bustanji, Mahmoud. (2004). A comparison of four methods for detecting the differential performance of the gender variable in the items of the Special Mental Abilities Test for the age group (15-16) years in Jordan. Unpublished doctoral thesis. Amman Arab University for Graduate Studies.
Crocker, Linda, and Algina, James (2009). An introduction to traditional and contemporary measurement theory, translation, let's, Zinat Yusef, 1st edition, Dar Al-Fikr Publishers and Distributors.
de Gruijter, D. N. M. & van der Kamp, L. J. Th. (2005). Statistical Test Theory for Education and Psychology. © D. N. M. de Gruijter & L. J. Th. Van der Kamp.
Dodouh, Hiba. (2017). The differential performance of the vocabulary in the classical theory and the Rasch model (a comparative statistical study). Unpublished master's thesis. Aleppo University: Syria.
Dodouh, Hiba. (2020). The effect of missing values processing methods on the accuracy of estimating parameters of some response theory models. Unpublished doctoral thesis. Aleppo University: Syria
Dodouh, Hiba. (2021). The effect of choosing the item response model (1PL, 2PL, 3PL, 4PL) and estimation methods on the parameters of the item and individuals and their accuracy. Wasit University Journal of Educational Sciences. Volume 1. Issue 44. pp. 449-478.
Embretson, S. E. & Reise, S. P. (2000). Item response theory for psychologists. Mahwah, NJ, US: Lawrence Erlbaum Associates Publishers.
Erguven, M. (2014). Two approaches to psychometric process: Classical test theory and item response theory. Journal of Education; ISSN 2298-0172.
Hambleton, R. K. & Swaminathan, H. (1985). Item Response Theory, Principles and Applications. Bston: Kluwer. Nijhoff Publishing amembers of the Kluwer Academic Publishers Group.
Hambleton, R. K., & Rogers, H. J. (1995). Item bias review (EDO-TM-95-9). Washington, DC: Clearinghouse on Assessment and Evaluation.
Hambleton, R.K. ; Swaminthan, H.; Rogers, h.j. (1991). Fundamentals Of Item Response Theory .Newbury Park,Ca:Sage. The International Professional Publishers.
Jensen, A. R. (1980). Précis of bias in mental testing. Behavioral and Brain Sciences, 3(3), 325-333.
Mahasneh, Ibrahim Mohamed (2013). Psychometrics under traditional theory and modern theory. 1st floor, Amman, Jarir House for Publishing and Distribution.
Obeidat, Thoukan. Adass, Abdel Rahman. Abdelhak, Kayed. (2000). Scientific research: (concept, tools, methods). Riyadh: Dar Osama for Publishing and Distribution.
RASCH, G. (1960). Probabilistic models for some intelligence and attainment tests (G. Leunbach, Trans.). Copenhagen: The Danish Institute for Educational Research.
Yaqoub, Ibrahim Muhammad Issa. (1990). A comparative study of the psychometric properties of the self-concept scale built using the traditional method and the Rasch model method. Unpublished doctoral thesis. University of Jordan. Graduate School.
