You are cordially invited to the webinar organized by the Department of Educational Sciences.
Speaker: İlker Kalender, PhD
Title: ” Classification Performance of the Computerized Adaptive Tests on the English Language Reading Proficiency Subtest”
Date: Friday, 24 December 2021
***This is an online event. To obtain Zoom link and password, please contact to the department.
Abstract: Computerized Adaptive Testing (CAT) procedures are widely used in testing to determine examinees’ locations on a latent construct’s continuum. Another essential role of testing is the classification of examinees. For language proficiency tests, this classification serves to categorize participants into different ability groups. Unfortunately, some misclassification is inevitable and may have significant consequences for stakeholders. Recent research suggests that classification efficacy may be enhanced using CAT. Using real data simulations, we investigated the classification performance of CAT on the reading section of an English language proficiency test and made comparisons with the paper-based version of the same test. Classification performance was examined using different indices by applying different locations and numbers of cut-off points. Results showed that classification was suitable when a single cut-off score was used, particularly for high and low ability test takers. Classification performance declined significantly when multiple cut-off points were simultaneously employed. The results highlight the potential of CAT to serve as classification purposes and outline avenues for further research.
About the speaker: Ilker Kalender completed his PhD on the applicability of computerized adaptive testing (CAT) procedures for university admission exams in Turkey. He joined Bilkent University in 2008. He worked at the Measurement, Selection and Placement Centre, conducting research projects involving developing computerized adaptive versions of language tests. He has also served in textbook examination committees for the Ministry of National Education. His research interests focus on CAT, large-scale data analysis, and student evaluations of teaching.