透過您的圖書館登入
IP:3.149.213.209

摘要


One of the biggest concerns in the implementation of computerized adaptive tests (CAT) is that some items in the item pool are overexposed while some items are underexposed or never administered. The purpose of this study is to present the conditional randomesque (CR) method and assess its performance using simulation based on real item pool data under various study conditions. The CR method is compared to the other two item selection methods: the none_IEC method and the Stocking and Lewis Conditional Multinomial method. The results show that there is some precision loss. However, the conditional and overall maximum item exposure rates are much smaller. In addition, the pool usage is greatly improved.

延伸閱讀