A method of determining the risk of mis-ranking a pair of examinees with a multiple-choice test was described. Assumptions of this method were that (1) questions guessed at were independent and had equally attractive options and (2) the ratio of the number of these questions to the number of options per question was at least 5 for each examinee.
Get full access to this article
View all access options for this article.
References
1.
WeitzmanR. A.Ideal multiple-choice items. Journal of the American Statistical Association, 1970, 65, 71–89.
