The Reliability and Validity of Multiple-Choice Exams in Large Introductory Courses
AAPT Meeting, Madison, WI, August 2003 (Contributed Talk)
The reliability and validity of fixed response (multiple choice) exams have been extensively studied for "professionally" written exams such as the SAT and GRE, and even the Force Concept Inventory. Much of the success of these multiple-choice exams is attributed to the careful construction of each question, as well as each response. In a study at the University of Illinois, Urbana-Champaign, we investigated the reliability and validity of a multiple-choice exam written for and administered in a large introductory physics course. The reliability of such a test is found using standard statistical methods. To determine the test's validity, we compared student ranking for a subset of students based on their multiple-choice score, graded explanations, and student interviews. In this talk we will share with you our findings and discuss whether or not multiple-choice exams are a reliable and valid way to rank students.