[1]李俊杰,郑慧婧,康春花*.变长非参数认知诊断自适应测验终止规则[J].江西师范大学学报(自然科学版),2022,(06):617-625.[doi:10.16357/j.cnki.issn1000-5862.2022.06.09]
　LI Junjie,ZHENG Huijing,KANG Chunhua*.The Variable Length Nonparametric Cognitive Diagnostic Adaptive Test Termination Rule[J].Journal of Jiangxi Normal University:Natural Science Edition,2022,(06):617-625.[doi:10.16357/j.cnki.issn1000-5862.2022.06.09]
点击复制

变长非参数认知诊断自适应测验终止规则()
分享到：

《江西师范大学学报》（自然科学版）[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2022年06期
页码:
617-625
栏目:
心理与教育测量
出版日期:
2022-11-25

文章信息/Info

Title:
The Variable Length Nonparametric Cognitive Diagnostic Adaptive Test Termination Rule
文章编号:
1000-5862(2022)06-0617-09
作者:
李俊杰1; 郑慧婧2; 康春花2*
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 100875; 2.浙江师范大学心理学院,浙江 金华 321004)
Author(s):
LI Junjie1; ZHENG Huijing2; KANG Chunhua2*
1.Collaborative Innovation Center of Assessment for Basic Education Quality,Beijing Normal University,Beijing 100875,China; 2.School of Psychology,Zhejiang Normal University,Jinhua Zhejiang 321004,China)
关键词:
变长;  非参数CD-CAT;  终止规则
Keywords:
variable length;  non-parametric CD-CAT;  termination rules
分类号:
B 841
DOI:
10.16357/j.cnki.issn1000-5862.2022.06.09
文献标志码:
A
摘要:
该文借鉴传统变长参数CD-CAT的终止规则,结合DWIR方法的指标提出2种非参数变长CD-CAT的终止规则:最大距离比例终止规则(MDRM)和距离比例双重标准终止规则(DRDSM).模拟研究发现:1)2种非参数终止规则MDRM和DRDSM适用于0-1计分和混合计分情境下的非参数CD-CAT测验; 2)当研究目的在于获得更加准确分类结果时,可在 MDRM 规则下的增大d1st值,或者在DRDSM规则下增大d1st值和减小d2nd值; 反之,可以减小d1st值或者增大d2nd值; 3)当测验终止的条件愈发严格时,即当d1st和P1st不断接近1或者d2nd和P2nd不断接近0时,采用MDRM或DRDSM作为测验终止规则的测验结果和采用后验概率作为终止规则的测验结果逐渐接近.
Abstract:
Firstly,referred to the termination rules of traditional variable length CD-CAT summarized before,the indicators in DWIR method are combined to propose two non-parametric termination rules of variable length CD-CAT that are maximum distance ratio method(MDRM)and distance ratio double standard method(DRDSM).The results showed that two nonparametric termination rules,MDRM and DRDSM,are suitable for nonparametric CD-CAT test in 0-1 scoring and multilevel scoring situations.When the purpose of the study is to obtain as accurate a classification result as possible,the d1st value under the MDRM rule can be increased,or the d1st value can be increased and d2nd value can be decreased under the DRDSM rule.On the contrary,it can be appropriately reduced.The conditions for test termination become more and more stringent,that is,d1st and P1st keep approaching 1 or d2nd and P2nd keep approaching 0,and the results that MDRM and DRDSM are used as test termination rules are gradually closer to the results that posterior probability is used as the same termination rule.

参考文献/References:

[1] CHENG Ying.When cognitive diagnosis meets computerized adaptive testing:CD-CAT [J].Psychometrika,2009,74(4):619-632.
[2] CHENG Ying.Improving cognitive diagnostic computerized adaptive testing by balancing attribute coverage:the modified maximum global discrimination index method [J].Educational and Psychological Measurement,2010,70(6):902-913.
[3] WANG Chun.Mutual information item selection method in cognitive diagnostic computerized adaptive testing with short test length [J].Educational and Psychological Measurement,2013,73(6):1017-1035.
[4] WANG Chun,CHANG Huhua,DOUGLAS J.Combining CAT with cognitive diagnosis:a weighted item selection approach [J].Behavior Research Methods,2012,44(1):95-109.
[5] XU Xueli,CHANG Huhua,DOUGLAS J.A simulation study to compare CAT strategies for cognitive diagnosis [EB/OL].[2022-02-16].https://www.semanticscholar.org/paper/A-Simulation-Study-to-Compare-CAT-Strategies-for-Xu-Chang/2b1144c924306aeb789f78e6dbc2124283032.
[6] 毛秀珍,辛涛.认知诊断CAT中项目曝光控制方法的比较 [J].心理学报,2013,45(6); 694-703.
[7] 陈平,辛涛.认知诊断计算机化自适应测验中在线标定方法的开发 [J].心理学报,2011,43(6):710-724.
[8] 陈平.认知诊断计算机化自适应测验的项目增补:以DINA模型为例 [D].北京:北京师范大学,2011.
[9] 汪文义,丁树良,游晓锋.计算机化自适应诊断测验中原始题的属性标定 [J].心理学报,2011,43(8):964-976.
[10] HSU C L,WANG Wenchung,CHEN Shuying.Variablelength computerized adaptive testing based on cognitive diagnosis models [J].Applied Psychological Measurement,2013,37(7):563-582.
[11] 郭磊,郑蝉金,边玉芳.变长CD-CAT中的曝光控制与终止规则 [J].心理学报,2015,47(1):129-140.
[12] CHANG Yuanpei,CHIU Chiayi,TSAI R C.Non-parametric CAT for CD in educational settings with small samples [J].Applied Psychological Measurement,2019,43(7):543-561.
[13] WEISS D J,KINGSBURY G.Application of computerized adaptive testing to educational problems [J].Journal of Educational Measurement,1984,21(4):361-375.
[14] BABCOCK B,WEISS D J.Termination criteria in computerized adaptive tests:variable-length cats are not biased [EB/OL].[2022-03-19].https://www.researchgate.net/profile/Ben-Babcock/publication/264878434_Termination_Criteria_in_Computerized_Adaptive_Tests_Variable-Length_CATs_Are_Not_Biased/links/543fbc910cf21227a11b3e69/Termination-Criteria-in-Computerized-Adaptive-Tests-Variable-Length-CATs-Are-Not-Biased.pdf.
[15] TATSUOKA C.Data analytic methods for latent partially ordered classification models [J].Journal of the Royal Statistical Society:Series C(Applied Statistics),2002,51(3):337-350.
[16] 李俊杰,马丽华,曾平飞,等.基于理想作答反应构建的非参CD-CAT选题策略 [J].心理科学,2022,45(2):470-480.
[17] JUNKER B W,SIJTSMA K.Cognitive assessment models with few assumptions,and connections with nonparametric item response theory [J].Applied Psychological Measurement,2001,25(3):258-272.
[18] MACREADY G B,DAYTON C M.The use of probabilistic models in the assessment of mastery [J].Journal of Educational Statistics,1977,2(2):99-120.
[19] HARTZ S M.A Bayesian framework for the unified model for assessing cognitive abilities:blending theory with practicality [D].Urbana-Champaign:University of Illinois at Urbana-Champaign,2002.
[20] HARTZ S M,ROUSSOS L A.The fusion model for skill diagnosis:blending theory with practicality [M].Princeton:Educational Testing Service,2008.
[21] 蔡艳,苗莹,涂冬波.多级评分的认知诊断计算机化适应测验 [J].心理学报,2016,48(10):1338-1346.
[22] 涂冬波,蔡艳,戴海琦,等.一种多级评分的认知诊断模型:P-DINA模型的开发 [J].心理学报,2010,42(10):1011-1020.
[23] XU Gongjun,WANG Chun,SHANG Zhuoran.On initial item selection in cognitive diagnostic computerized adaptive testing [J].British Journal of Mathematical and Statistical Psychology,2016,69(3):291-315.
[24] CHIU Chiayi,DOUGLAS J.A nonparametric approach to cognitive diagnosis by proximity to ideal response patterns [J].Journal of Classification,2013,30(2):225-250.
[25] CHIU Chiayi,Köhn H F.Consistency theory for the general nonparametric classifification method [J].Psychometrika,2019,84(3):830-845.
[26] WANG Shiyu,DOUGLAS J.Consistency of nonparametric classifification in cognitive diagnosis [J].Psychometrika,2015,80(1):85-100.
[27] CHIU Chiayi,DOUGLAS J A,LI Xiaodong.Cluster analysis for cognitive diagnosis:theory and applications [J].Psychometrika,2009,74(4):633-665.
[28] 孙小坚,毛秀珍,宋乃庆,等.定长CD-CAT中两种新的题目曝光控制方法 [J].心理科学,2021,44(1):205-213.

备注/Memo

备注/Memo:
收稿日期:2022-06-17
基金项目:教育部人文社会科学青年基金(22YJA190005)资助项目.
通信作者:康春花(1974—),女,江西弋阳人,副教授,博士,主要从事心理测量与评价研究.E-mail:akang@zjnu.edu.cn
更新日期/Last Update: 2022-11-25