Efficient Creation of E-Assessment by Redefining Questions Items Using IRT

  • Nabila Jannat Department of Computer Science and IT, Alhamd Islamic University, Islamabad, Pakistan
  • Muhammad Yasir Imam
  • Adnan Naseem Department of Computer Science and IT, Alhamd Islamic University, Islamabad, Pakistan
  • Saman Fatima Department of Computer Science and IT, Alhamd Islamic University, Islamabad, Pakistan
  • Kashaf-ul-Khair Department of Computer Science and IT, Alhamd Islamic University, Islamabad, Pakistan
Keywords: Assurance Technologies, Software Engineering, Software Evaluation, Item Response Theory

Abstract

Different student evaluation techniques are being used to evaluate students learning abilities. Most of learning techniques follow different evaluation methods but Item Response Theory (IRT) has strong impact among them. Mostly evaluation techniques lack some important evaluation measure such as difficulty level, time index and discrimination level. By redefining questions with the help of IRT, enhanced e-assessment method to be more accurate in terms of difficulty, time and discrimination level. This study will ease the examiners abilities to access the criteria of difficulty of exam. To check the level of difficulty and examiner’s abilities accordingly, IRT will be suitable technique to follow. IRT can make a strong influence on aptitude tests like GAT, GRE etc. Meanwhile, many other job-related tests will be scheduled with the help of IRT. This method helps test makers to divide and allocate the time for every question to be asked in test. The IRT generates the test more effectively. Testing authorities and students can take equally benefit from this method

Published
2020-12-30
How to Cite
Nabila Jannat, Muhammad Yasir Imam, Adnan Naseem, Saman Fatima, & Kashaf-ul-Khair. (2020). Efficient Creation of E-Assessment by Redefining Questions Items Using IRT. University of Sindh Journal of Information and Communication Technology , 4(4), 262 - 267. Retrieved from https://sujo.usindh.edu.pk/index.php/USJICT/article/view/3329

Most read articles by the same author(s)

Obs.: This plugin requires at least one statistics/report plugin to be enabled. If your statistics plugins provide more than one metric then please also select a main metric on the admin's site settings page and/or on the journal manager's settings pages.