A necessary and sufficient condition for a perfectly homogeneous test in the sense of Loevinger is stated and proved. Using this result, a formula for computing the maximum possible KR-20 when the test variance is assumed fixed is presented. A new index of test homogeneity is also presented and discussed. (Author/BW)

The magnitude of statistical bias for the phi-coefficient was investigated, using computer simulated examinations in which all the students had equal knowledge. Several modifications of phi were tested, but when applied to real examinations, none succeeded in improving its reproducibility when items are re-used on equivalent student groups.…

On a multiple-choice test in which each item has k alternative responses, the test taker is permitted to choose any subset which he believes contains the one correct answer. A scoring system is devised. (Author/CTM)

A modification of the method of reciprocal averages for scaling multiple choice data is proposed. The proposed method handles the data in a piecewise fashion and allows for faster convergence to a solution. (Author/JKS)

Aims to help instructors make more valid test questions, particularly multiple-choice ones. Emphasis is placed on multiple-choice questions to show the wealth of opportunities they offer for testing because of their uses, objectivity, and ease of grading. Discusses test scheduling, construction, and evaluation and follow-up. (CT)

In scoring multiple-choice tests, a score of 1 is given to right answers, 0 to unanswered questions, and some negative score to wrong answers. This paper discusses the relation of this negative score to the assumption made about the partial knowledge with the subjects may have. (Author/GDC)

When correlations between actual university classroom cheating behavior (multiple-choice answer copying) and pretest estimates of success, confidence, and test importance were studied answer copying correlated positively with estimates of success. Confidence in these estimates of success also correlated positively with answer copying, while…

Divgi's contention that the Rasch model should not be applied to multiple-choice test items is refuted. As with any measurement model, the burden is on the model user to establish that assumptions have been met and that generalizations are warranted for any application, including applications involving multiple-choice tests. (TJH)

Describes a simple and novel method for identifying misconceptions. Utilizes the Certainty of Response Index (CRI) in conjunction with answers to multiple-choice questions. (Author/CCM)

Undergraduates (n=187) were given information booklets; experimentals took either a multiple-choice (n=64) or short-answer (n=64) test afterward. Both groups and 60 controls were tested 3 weeks later on new and previously tested information. Both multiple-choice and short-answer tests were better than no test in improving retention. Multiple…

Multiple-choice questions are the basis of a significant portion of assessment in introductory economics courses. However, these questions, as found in course assessments, test banks, and textbooks, often fail to evaluate students' abilities to use and apply economic analysis. The authors conclude that multiple-choice questions can be used to…

Content mastery and self-efficacy were measured at the beginning and at the end of two classes in Research Methods in Psychology. A multiple-choice test measured content mastery and a questionnaire measured self-efficacy. Self-efficacy reports improved significantly over the course of instruction, as did examination performance. The correlation…