Weighted Scoring of Multiple-choice Questions based Exams: Expert and Empirical Weighting Factors

摘要

The increasing number of students per class and the limited teaching resources are important factors for increasing the popularity of multiple-choice questions based (MCQ) exams amongst the academic tutors. Weighted grading of MCQ items is compatible with a wide range of options, therefore it can reward those students who have successfully answered the most demanding items. In the case of weighted scoring of a MCQ based exam, the weighting factor of each item can be obtained a priori from an expert of the domain, usually the lecturer, or a posteriori by some empirical method. The overall score of a student is calculated as the weighted average of the items successfully answered. This publication presents an iterative method for scoring MCQ based examinations. The proposed method attempts to achieve the best possible congruence of the overall student scores calculated as the weighted average based on expert and empirical weighting.