PARAMETER ESTIMATION IN A NEW MULTIPLE CHOICE ITEM RESPONSE MODEL

Abstract

We propose a new response model for multiple choice items, which is an extension of the three-parameter logistic model. This model enables us to make use of the information provided by distractors as well as correct item alternatives. The essential idea of this model is the further partition of the incorrect response curves in terms of the weighted average of the“ideal”correct curve and incorrect curve. By using artificial data, we showed that this model can produce better estimates of the ability parameters than the usulal three parameter logistic model.