Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
P-Index
This Author published in this journals
All Journal Indonesian Journal of Applied Science and Engineering
Guldana Begimbetova
Abai Kazakh Pedagogical University

Published : 1 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 1 Documents
Search

 1 
Item Analysis of an English Achievement Test Using Rasch Model and Classical Test Theory Rezkilaturahmi Rezkilaturahmi; Nur Hidayanto Pancoro Setyo Putro; Guldana Begimbetova; Oscar Ndayizeye; Muthmainnah Muthmainnah; Dinda Khaira Latifa
Indonesian Journal of Applied Science and Engineering Vol. 3 No. 1 (2025)
Publisher : Peneliti Teknologi Teknik Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59247/ijase.v3i1.180

Abstract

This study aimed to evaluate the quality of English test items developed by the English Teachers Working Group (MGMP) in Muna District, Indonesia. The study specifically examined the psychometric characteristics of the items in terms of item difficulty, discrimination, distractor effectiveness, and item fit using Classical Test Theory (CTT) and Item Response Theory (IRT). This study employed a quantitative psychometric approach. The data consisted of responses to an English achievement test developed and administered by English teachers participating in the MGMP in Muna District. Item quality was initially examined using Classical Test Theory based on item difficulty, discrimination index, and distractor effectiveness. Further analysis was conducted using the Rasch model of Item Response Theory with the Quest program to evaluate item difficulty and item fit based on INFIT Mean Square (MNSQ) statistics. The results of both approaches were used to determine whether individual items were acceptable, required revision, or should be rejected. The analysis revealed variation in the psychometric quality of the test items. The CTT analysis showed differences in item difficulty, discrimination, and distractor effectiveness, while the Rasch analysis revealed variation in item difficulty and item fit. The combined findings indicated that some items demonstrated acceptable psychometric characteristics, whereas others required revision. In addition, several items could not be evaluated using Quest. These findings indicate that although more than half of the items demonstrated acceptable psychometric characteristics, a substantial proportion still requires improvement before being used as a high-quality English assessment.
Co-Authors Dinda Khaira Latifa Muthmainnah Muthmainnah Nur Hidayanto Pancoro Setyo Putro Oscar Ndayizeye Rezkilaturahmi Rezkilaturahmi