Comparing confidence-based and conventional scoring methods: The case of an English grammar class

Abstract

This study aimed at investigating the reliability, predictive validity, and self-esteem and gender bias of confidence-based scoring. This is a method of scoring in which the test takers receive a positive or negative point based on their rating of their confidence in an answer. The participants, who were 49 English-major students taking their grammar course, were given 8 multiple-choice tests during the semester. These tests were scored both conventionally and in a confidence-based manner, and the reliabilities of these two score sets were compared. Each score set was correlated with the final exam scores to compare their predictive validity. Gender and self-esteem bias of the confidence-based scores of the eight tests were also calculated. The results showed that there was no difference between the reliabilities of the two sets of scores. Confidence-based scores had better predictive validity than conventional scores, but this difference was not significant. Confidence-based scores were not biased against a specific gender and specific levels of self-esteem. The conclusion is that confidence-based scoring is as good as conventional scoring and the choice between these two scoring methods depends on the teacher's discretion and the teaching context.