纵向非参数认知诊断评估  

Nonparametric Methods for Longitudinal Cognitive Diagnosis

作　　者：郑天鹏 郭磊 边玉芳[1,4,5] ZHENG Tian-peng;GUO Lei;BIAN Yu-fang(Collaborative Innovation Center of Assessment toward Basic Education Quality(CICA-BEQ)at Beijing Normal University,Beijing 100088,China;Faculty of Psychology,Southwest University,Chongqing 400715,China;Southwest University Branch,Collaborative Innovation Center of Assessment toward Basic Education Quality,Chongqing 400715,China;Child and Family Education Research Center at Beijing Normal University,Beijing 100088,China;Institute of Mental Health and Education at Beijing Normal University,Beijing 100088,China)

机构地区：[1]北京师范大学中国基础教育质量监测协同创新中心,北京100088 [2]西南大学心理学部,重庆400715 [3]中国基础教育质量监测协同创新中心西南大学分中心,重庆400715 [4]北京师范大学儿童家庭教育研究中心,北京100088 [5]北京师范大学心理健康与教育研究所,北京100088

出　　处：《应用心理学》2024年第2期172-183,共12页Chinese Journal of Applied Psychology

基　　金：北京师范大学中国基础教育质量监测协同创新中心研究生自主课题(BJZK-2021A1-20010);中央高校基本科研业务费专项资金(SWU2109222)。

摘　　要：通过建立相邻时间点间被试知识状态和理想作答模式的链接,提出了4种逻辑简洁的纵向非参数认知诊断方法:LNPC、LWNPC、LGNPC和LWGNPC。模拟研究结果表明:建立的链接能提升纵向判准精度。与参数模型相比,4种方法估计精度相当,受样本容量影响小。与Long-HDD相比,4种方法判准精度较高,题目质量较低时LNPC和LWNPC仍有较好表现;实证研究表明:4种方法能够应用于实际纵向测验分析,与参数模型和Long-HDD判别一致性较高。推荐LWNPC方法。This research proposed four concise longitudinal nonparametric diagnostic methods:longitudinal nonparametric classification(LNPC),longitudinal weighted nonparametric classification(LWNPC),longitudinal generalized nonparametric classification(LGNPC),and longitudinal weighted generalized nonparametric classification(LWGNPC),by leveraging the connection of students’knowledge state and the ideal response pattern between adjacent time points.The performance of the four new methods was evaluated by two simulation studies and an empirical study.The results of simulation studies showed that:(1)the established link could improve the accuracy of longitudinal classification;(2)compared to the HO-HMM model,the new methods could achieve similar precision while being less affected by the sample size;(3)the new methods outperformed the Long-HDD method in terms of accuracy,and the LNPC and LWNPC still performed well even with low-quality items.The results of the empirical study showed that the four new methods were highly consistent with the HO-HMM model and Long-HDD classification.We recommend using the LWNPC method to analyze the real data.

关 键 词：非参数方法 纵向认知诊断评估 海明距离 判准精度 

分 类 号：B841[哲学宗教—基础心理学]