Purification procedures used for the detection of gender DIF: Item bias in a foreign language test
[ X ]
Tarih
2023
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Izzet Kara
Erişim Hakkı
info:eu-repo/semantics/openAccess
Özet
In the current study, differential item functioning (DIF) detection using real data was conducted with the application of Mantel-Haenszel (MH), Simultaneous item bias test (SIBTEST), Lord's chi-square, and Raju's area methods, both when item purification was carried out and when item purification was not. After detecting gender-related DIF, expert opinions were obtained for a bias study since it is important to conduct gender bias research in the English test. Additionally, in the relevant literature, there were some DIF studies, but not completely similar bias studies. The sample of the research consisted of 7,389 students who took the Transition from Primary to Secondary Education Exam (TPSEE, referred to as TEOG in Turkish) administered in April 2017. When gender-related DIF analysis was performed with the aforementioned four methods, the results were found to differ partially. DIF analysis results differed in different conditions based on whether item purification was performed or not. Furthermore, the detection of DIF was indicative of potential bias. In the second stage of the study, the opinions of seven experts were sought for item 11, for which DIF was detected at least at B level based on MH, SIBTEST. As a result of expert opinion, it was established that there was no bias based on gender in any of the items in the English test. It is advised that akin bias studies be carried out to enable test developers to be aware of characteristics that may result in item bias and construct unbiased items.
Açıklama
Anahtar Kelimeler
Mantel-Haenszel,, Simultaneous item bias test, Lord's chi-square, Raju's unsigned area, Bias, Item purification
Kaynak
International Journal of Assessment Tools in Education
WoS Q Değeri
N/A
Scopus Q Değeri
N/A
Cilt
10
Sayı
4
