An Appraisal of Methods Investigating DIF in Language Assessment

سال انتشار: 1397
نوع سند: مقاله کنفرانسی
زبان: انگلیسی
مشاهده: 429

متن کامل این مقاله منتشر نشده است و فقط به صورت چکیده یا چکیده مبسوط در پایگاه موجود می باشد.
توضیح: معمولا کلیه مقالاتی که کمتر از ۵ صفحه باشند در پایگاه سیویلیکا اصل مقاله (فول تکست) محسوب نمی شوند و فقط کاربران عضو بدون کسر اعتبار می توانند فایل آنها را دریافت نمایند.

استخراج به نرم افزارهای پژوهشی:

لینک ثابت به این مقاله:

شناسه ملی سند علمی:

ELSCONF06_130

تاریخ نمایه سازی: 8 تیر 1398

چکیده مقاله:

A plethora of methods for detecting Differential Item Functioning (DIF) has been suggested during the last couple ofdecades. This study has aimed to investigate the comparability of results from three widely used DIF detectiontechniques: the Rasch model, Logistic Regression, and Mantel-Haenszel (MH). The data comes from an administrationof the University of Tehran English Proficiency Test (UTEPT) which is a high-stakes test administered annually to PhDcandidates. An analysis of uniform DIF by the three techniques indicated that three items show large DIF. Logisticregression did not flag any items for DIF while the MH detected two items with moderate DIF. None of the items wereflagged for non-uniform DIF by either the Rasch model or logistic regression. The items that displayed strong uniformDIF in the Rasch model were flagged for moderate DIF by the MH and only small DIF by logistic regression. All in all,the results indicated that the Rasch model is the most liberal method while logistic regression is the most conservative.An analysis of Differential Test Functioning using the Rasch model also indicated that the test might not be functioningequally for the two groups.

نویسندگان

Hossein Karami

University of Tehran, Tehran, Iran

Ali Khodi

University of Tehran, Kish International Campus