Please use this identifier to cite or link to this item:

IRT Discrimination Interpretation in Criterion-Referenced Language Testing

File SizeFormat 
Hudson (1990)_WP9(2).pdf6.57 MBAdobe PDFView/Open

Item Summary

Title: IRT Discrimination Interpretation in Criterion-Referenced Language Testing
Authors: Hudson, Thom
Issue Date: 1990
Abstract: This study investigates relationships among the IRT one-parameter fit statistics, the two-parameter slope parameter and traditional biserial correlations in terms of the role these indices play in criterion-referenced language test construction. It discusses the assumptions of the two models and how these assumptions can affect criterion-referenced test construction and interpretation. The study then specifically examines how the indices operate in terms of item discrimination when items are designed to determine whether or not and examinee is at a specific level of ability. Examinees in Mexico, Saudi Arabia and Japan were administered one of two forms of a functional test containing (Form A n=430, k=94: Form B n=400, k=95). The data were analyzed using the two IRT models and the results were compared. The results indicate strong relationships between biserial correlation, two-parameter slope, and one-parameter infit and outfit. The implications of these strong relationships for interpreting the indices are discussed.
Pages/Duration: 30 pages
Appears in Collections:Working Papers

Items in ScholarSpace are protected by copyright, with all rights reserved, unless otherwise indicated.