摘要
高效安全的选题策略是计算机化自适应测验追求的目标.最大Fisher信息量选题测验效率高、能力估计准确,但项目调用不均匀,影响考试的安全;而增设影子题库能较好地平衡项目调用的均匀性.根据上述2种选题策略的优缺点,在0-1评分模型下,结合影子题库得到一种新的选题策略,并在按a分层、按最大信息量分层中引入了新的选题方法.计算机模拟实验显示:新的选题方法效果比较理想.
Computerized Adaptive Testing（CAT） has been in pursuit of the goal is to develop both efficient and safe item selection strategies. It is well known that there is a typical selection strategy called Maximum Fisher Information （MFI）. However, this strategy has its advantages together with its downsides. On the one hand, MFI method can ob- tain high efficiency and accurate estimation of ability;on the other hand, its uneven item selection may lead to the insecurity of examination. Meanwhile, though shadow bank can be a good method of the item called evenly, it may result in the inefficiency of the test. Taking the advantages and disadvantages of the two selection strategies in the 0-1 scored CAT into consideration, a new item selection strategy is proposed in this paper, and pull this new method in α-Stratification（α-STR） and Maximum Information Stratification （MIS）. The computer simulation shows that the new method works ideally.
出处
《江西师范大学学报（自然科学版）》
CAS
北大核心
2013年第6期657-660,共4页
Journal of Jiangxi Normal University(Natural Science Edition)
基金
国家自然科学基金(30860084
31160203
31100756
31360237
31300876)
国家社会科学基金(12BYY055)
江西省教育厅科技计划(GJJ13207
GJJ13227
GJJ13226
GJJ13208
GJJ13209
13JY01)资助项目
