Investigation of item difficulty, item discrimination, and distractor analysis of a reading test in Sri Lankan context

Abstract

This research was conducted by designing a reading test evaluating the socio-cognitive processing skills prescribed by Khalifa and Weir (2009). The test design was created using a guided table of specifications consisting of 25 items. The test responses of 50 students were evaluated to check for the validity and reliability of the test. The validity of the test is proven through the item analysis. The item analysis involving the item difficulty indices, item discrimination indices, and distractor analysis was investigated for each item to provide detailed information leading to the improvement of test construction. The descriptive statistics were used to interpret the results achieved from the analysis of 25 test items computed using Microsoft Office Excel. The results of the study revealed that the test met the standards for content validity, which was characterised as a good validity indicating acceptable item difficulty indices having 17 items as moderate. Besides the 3 poor functioning items, all the other items function well to discriminate the high ability students from the low ability ones. According to the test scores, students were categorized into five levels belonging to the CEFR A1 to C2 levels. It signifies that more than half of the test items which means 88% of them are well functioning and the test proves to be valid and reliable. The present research can contribute to the students, teachers, and test-makers to have an insightful understanding of item analysis and test development.