Semi-real-time Analyses of Item Characteristics for Medical School Admission Tests

0478547 - ÚI 2018 RIV PL eng C - Conference Paper (international conference)
Martinková, Patrícia - Štěpánek, L. - Drabinová, Adéla - Houdek, Jakub - Vejražka, M. - Štuka, Č.
Semi-real-time Analyses of Item Characteristics for Medical School Admission Tests.
Proceedings of the 2017 Federated Conference on Computer Science and Information Systems. Warszawa: Polish Information Processing Society, 2017 - (Ganzha, M.; Maciaszek, L.; Paprzycki, M.), s. 189-194. Annals of Computer Science and Information Systems, 11. ISBN 978-83-946253-7-5. ISSN 2300-5963.
[FedCSIS 2017. Federated Conference on Computer Science and Information Systems. Prague (CZ), 03.09.2017-06.09.2017]
Institutional support: RVO:67985807
Keywords : admission test development * item analysis * item difficulty * item discrimination * R * shiny * přijímací testy * položková analýza * obtížnost položky * diskriminace položky
OECD category: Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

University admission exams belong to so-called highstakes tests, i. e. tests with important consequences for the exam taker. Given the importance of the admission process for the applicant and the institution, routine evaluation of the admission tests and their items is desirable. In this work, we introduce a quick and efficient methodology and on-line tool for semi-real-time evaluation of admission exams and their items based on classical test theory (CTT) and item response theory (IRT) models. We generalize some of the traditional item analysis concepts to tailor them for specific purposes of the admission test. On example of medical school admission test we demonstrate how R-based web application may simplify admissions evaluation work-flow and may guarantee quick accessibility of the psychometric measures. We conclude that the presented tool is convenient for analysis of any admission or educational test in general.
Permanent Link: http://hdl.handle.net/11104/0274642