自动控制区分度作用的选题策略研究
The Study of Item Selection Strategy-Automatic Control for the Role of Discrimination Index

沿用引入曝光控制因子的CAT选题策略中所提出的曝光控制因子,同时将定长测验的测验长度以及不定长测验中被试累积信息量加入到新选题策略中,提出了在不分层的条件下自动控制区分度作用的选题策略.蒙特卡洛模拟结果表明:新方法在项目调用均匀性、测验效率等评价指标上效果均较为理想.
Combining the exposure control factor proposed by Cheng Xiao-yang with the ratio of the test length administered for fixed tests or the ratio of the test information administered for variable length tests to construct a new item selection strategy,and the new strategy can control the role of discrimination index automatically without stratification of the item pool during the course of computerized adaptive testing.The results of Monte Carlo simulations show that the new approach is more ideal in the performance of item exposure control and test efficiency and other indexes