Using classical test theory to analyze multiple – choice questions

Trung Hieu Nguyen1, , Bich Nhu Nguyen1
1 Soc Trang Pedagogics College

Main Article Content

Abstract

The article reports the result of using Classical Test Theory to analyze multiple – choice questions. The statistical method was used to examine an already-used test of 30 items with 85 student responses. The findings indicate that Classical Test Theory can be used to analyze test item parameters such as item difficulty, item discrimination, and distractor quality. These test item parameters play an important role in standardizing and enhancing the quality of multiple – choice questions. Standardized tests ensure the accuracy, objectiveness and fairness in assessing student learning outcomes.

Article Details

References

[1]. Robert L. Brennan (2011), “Generalizability Theory and Classical Test Theory”, Applied Measurement in Education, 24: 1–21.
[2]. Ebel, R. L. (1965), Measuring Educational Achievement, Englewood Cliffs: Prentice - Hall.
[3]. Osterlind, S. J. (1989), Constructing test items, Boston: Kluwer Academic.
[4]. Lâm Quang Thiệp (2008), Trắc nghiệm và ứng dụng, NXB Khoa học và Kỹ thuật, Hà Nội.
[5]. Margaret Wu, Hak Ping Tam, Tsung-Hau Jen (2016), Educational Measurement for Applied Researchers: Theory into Practice, Springer Nature Singapore Pte Ltd.