引入曝光因子的最大信息量动态分层法

摘要

As far as Computerized Adaptive Testing(CAT)is concerned,the issue of item selection strategy has received more attention because of its vital role. It’s well know that a-Stratified Method(a-STR)is the most unique and widely used among the item selecting methods. However,a-STR has its advantages together with its downsides. The Dynamic a-Stratified Method(DAS)was presented according to a-STR’s limitations,but its efficiency and exposure control is not very good. Therefore,in 0-1 scored CAT,a new item selection strategy is proposed in this paper to improve the DAS by introducing the Exposure-Control Factor and the Maximum Information Stratification Method. The results of Monte Carlo simulations show that compared with DAS,the approach proposed in this paper is more effective in terms of exposure control and more ideal in the performance of other indexes.%　　在计算机化自适应测验(CAT)中,a分层法(a-STR)是较为独特且运用较广的一种选题策略,它可以有效控制题目曝光率以提高测验的安全性。动态a分层法(DAS)是针对a-STR分层数固定不变,需要人为在考试前确定且没有失效时间等一些不足提出的一种选题策略,但DAS本身在测验效率和曝光率控制上的表现并不优秀,对此,在0-1评分的CAT中,通过引入曝光因子(ecf)和最大信息量分层策略(MIS),提出一种复合型选题策略,以期对DAS进行改进。计算机模拟结果显示,新的选题策略在测验效率和曝光率控制方面均优于DAS,达到了研究的目的。