An investigation of enhancement of ability evaluation by using a nested logit model for multiple-choice items

Multiple-choice items are wildly used in psychological and educational test. The present study investigated that if a multiple-choice item have an advantage over a dichotomous item on ability or latent trait evaluation. An item response model, 2-parameter logistic nested logit model (2PL-NLM), was used to fit the multiple-choice data. Both simulation study and empirical study indicated that the accuracy and the stability of ability estimation were enhanced by using multiple-choice model rather than dichotomous model, because more information was included in multiple-choice items' distractors. But the accuracy of ability estimation showed little differences in four-choice items, five-choice items and six choice items. Moreover, 2PL-NLM could extract more information from low-level respondents than from high-level ones, because they had more distractor chosen behaviors. In the empirical study, respondents at different trait levels would be attracted by different distractors from the Chinese Vocabulary Test for Grade 1 by using the changing traces of distractor probabilities calculated from 2PL-NLM. It is suggested that the responses of students at different levels could reflect the students' vocabulary development process.