Combining multiple-choice and constructed-response test scores: An economist's view

There exists considerable evidence from educational measurement theorists that constructed-response questions add little new information about student achievement beyond that provided by multiple-choice questions. The purpose of this study was to view this issue through the eyes of an economist, focusing on the bottom line of how many misclassifications of students would occur by replacing the constructed-response portion of the Advanced Placement exams in economics with more multiple-choice questions. A novel computer simulation methodology was employed, and it was discovered that some students do better on one type of test than on the other and that this gives rise to a small but statistically significant number of misclassifications.