Volume 8, number 1
 PDF Downloads: 1088

Assessing the Psychometric Indices of Written Multiple Choice Educational Examinations of College of Paramedics of Kashan University of Medical Sciences in Education Year 2008-09

Mansour Sayyah*, Zarichehr Vakili¹ and Manzardokht Bigdeli

Affiliated Faculty Membe of Educational Development Center (EDC)- College of Medicine, Kashan University of Medical Sciences, Kashan (Iran).

ABSTRACT: Evaluation of students’ academic achievement is one of the most important affair in any educational setting. The majority of educational institutions use multiple choice exams to evaluate their students. The question items making up these exams need to possess certain psychometric properties if an exam is to be regarded as reliable instruments. Such property is amenable to examination by item analysis. The purpose of this research was to examine the multiple choice exams used in paramedic college of Kashan University of Medical Science in year 2008-9. In this cross sectional descriptive study, the responses of students to the multiple choice exams as well as the correct responses to each item provided by the instructor in education year 2008-9 was used. All the multiple choices exams conducted in this period were used by codes so that the identity of the instructor as well as the student was kept confidential. The difficulty index, discrimination index, and Cronbach alpha was calculated for every exam and then means value for each index was calculated by LERTAL 5.0 software purchased from Assessment Systems Corporation of the United States to perform item analysis. Statistical Analysis A total of 1481 multiple choice question items presented to the students at the college of paramedics for evaluating 31 different subjects was analyzed. The results of analysis showed that the mean value of difficulty items, discrimination index and Cronbach alpha were 0.55, 0.36 and 0.82, The average of difficulty index of multiple choice exams of college of paramedic was 0.55. This value is within the recommended value of 0.6 to 0.7 purposed by Granlond ( 1985) and Nelson (2001) range 0.3 to 0.7. The average of discrimination index 0.36 is also higher than the 0.21 regarded as acceptable value by Nelson. The average of Cronbach alpha was acceptable for most of the exams, however, some of the tests had value less than the recommended value and needs careful reexamination. In addition, some of the items in the test had negative discrimination index and need to be revised in future tests. Further research is needed to construct more reliable tests.

KEYWORDS: Item Analysis; Difficulty index; discrimination index; Cronbach alpha; multiple choice exams.

Download this article as: 

[ HTML Full Text]

Back to TOC