| dc.description.abstract |
This paper presents an analysis of the academic listening test (ALT) utilizing Rasch analysis, which has been utilized as a test development method. Through the analysis this study investigates what has been measured at ALT during three academic semesters. Along with the Rasch analysis, classical item theory was also applied to analyze the current data. The results by the Racsh analysis indicated that the most of the ALT that consistently assessed the students’ academic listening ability from low to high. The analysis of misfit and the classical item statistics pointed out some potentially misfitting items on the ALT, indicating that they were candidates for revision. This paper further discusses how it is viable for test developers to apply the Rasch model for the construction, analysis, and possible revision of a listening subtest for the purpose of placement testing. |
en_US |