Journal of Psychological Science ›› 2022, Vol. 45 ›› Issue (2): 470-480.

Previous Articles     Next Articles

A Non-parametric CD-CAT Selection Strategy Based on Ideal Response

  

  • Received:2020-06-27 Revised:2021-09-07 Online:2022-03-20 Published:2022-12-11
  • Contact: Chun-Hua KANG

基于理想作答反应构建的非参CD-CAT选题策略

李俊杰1,马丽华1,曾平飞2,康春花2   

  1. 1. 浙江师范大学
    2. 浙江师范大学教师教育学院
  • 通讯作者: 康春花

Abstract: Cognitive Diagnostic Adaptive Testing (CD-CAT) is featured with its Adaptive characteristics, and it is able to conduct Adaptive diagnosis and feedback on students' knowledge status.In today's personalized education, CD-CAT has a good development prospect and will play an important role in the future educational practice, so it has increasingly become a research hotspot at home and abroad.Topic selection strategy has always been one of the most concerned techniques in CD-CAT. Therefore, many researchers have put forward many topic selection strategies, such as KL, PWKL, SHE, MI and their variants.Most of these strategies are based on a certain amount of information and belong to the parameter category.Although the above parameter selection strategy has a good performance in the research, it also has the following shortcomings: First, in the process of building the question bank, a large number of questions in the test bank should be used in advance, and the test data should be used for parameter estimation, so as to ensure the accuracy of the parameter estimation.Such a large number of samples is not easy to realize in practice, especially in the course teaching.Second, the selection strategy of parameters is generally selected only for those topics with good quality, which will make the exposure rate of some topics too high and threaten the security of the question bank.Thirdly, the selected topic strategy models of parameters are complex, with large computational burden and difficult to understand. In recent years, researchers have developed a simple and effective non-parametric cognitive diagnosis method is suitable for small sample (HDD, EDD, MDD). Therefore, this study based on the thought of distance discriminant method, try to put aside the multifarious calculation formula and parameter estimation, based on the ideal answer, according to have title of each response is courtesy of model build different attributes control the distance weighting function, change numerous for brief, developed two kinds of suitable for hybrid scoring non-parametric CD - CAT DWIR and HDWIR topic selection strategy.The effects of DWIR and HDWIR were explored through two simulation studies. Study 1: Comparison was made between DWIR and HDWIR and selected topic strategies without exposure control (PS-KL and PS-PWKL).Study 2: Comparison between DWIR, HDWIR and selected topic strategy with exposure control.The results show that :(1)DWIR and HDWIR algorithms are simple and easy to understand, with few preconditions and easy to meet application conditions;(2)DWIR and HDWIR have wide applicability. They can be used not only for the topic selection of 01 scoring and multilevel scoring, but also for the parameter CD-CAT and non-parameter CD-CAT.(3) The attribute classification accuracy of DWIR and HDWIR is higher than that of the parameter selection strategy with exposure control, and the selection speed is faster.(4)DWIR and HDWIR have good exposure control effect, and the selection strategy is based on exposure control, so there is no need to add exposure control in the selection strategy to simplify the selection strategy.

Key words: cognitive diagnosis, computer adaptive test, non-parameter selection, strategy, classification, accuracy, exposure control

摘要: 研究提出了两种简单有效且适用于混合计分的非参数选题策略(DWIR和HDWIR),通过模拟研究将DWIR和HDWIR与参数的选题策略比较,结果发现:(1)DWIR和HDWIR算法简单,容易理解,前提条件少,应用条件易满足;(2)DWIR和HDWIR适用性广,不仅可用于01计分和多级计分的题目选题,亦适用于参数的CD-CAT和非参数的CD-CAT;(3)DWIR和HDWIR的属性分类准确性高于带曝光控制的参数选题策略,且选题速度较快;(4)DWIR和HDWIR的曝光控制效果好,且为自带曝光控制的选题策略,无需在选题策略中外加曝光控制,简化选题策略。

关键词: 认知诊断计算机自适应测验 非参数选题策略 分类准确性 曝光控制