THE USE OF RASCH MEASUREMENT MODEL IN ENGLISH TESTING

• Published in: Cakrawala pendidikan : CP Vol. 38; no. 1; pp. 16 - 32
• Main Authors: Mokshein, Siti Eshah, Ishak, Haliza, Ahmad, Hishamuddin
• Format: Journal Article
• Language: English
• Published: Universitas Negeri Yogyakarta 08.02.2019
• Subjects: item analysis; rasch measurement model; validity and reliability
• ISSN: 0216-1370; 2442-8620
• DOI: 10.21831/cp.v38i1.22750

This study aimed at determining the quality of the English Paper 1 (EP1) items of UPSR trial examination for six graders in terms of its reliability, validity and items characteristics. It also sought to determine the difficulty levels of 40 multiple-choice items consisting five constructs of vocabulary, language and social expression, grammar, cloze-comprehension and reading comprehension. A number of 525 primary schools students were randomly selected from 3876 students in Kuala Selangor, Malaysia. Using the Rasch measurement model, the validity evidences were shown through the results of Principle Component Analysis (PCA), fit statistics and item distractor analysis. The results from PCA analysis showed the absence of second dimension in the test, which met the assumption of modern testing theory. Fit statistics analyses have identified seven misfit items that are beyond the acceptable range (0.7 - 1.3 logit). Item distractor analysis has identified five problematic items whereby three of them are also misfit items. Summary statistics shows that the reliability indices of Cronbach’s Alpha were greater than 0.80 and separation indices were greater than 2. This study would benefit teachers in improving existing assessment practice by spreading out the importance of item analysis in schools, particularly in language testing.