[1]喻晓锋,马奕帆,罗照盛,等.基于K2算法的属性层级结构学习研究[J].江西师范大学学报(自然科学版),2021,(04):376-383.[doi:10.16357/j.cnki.issn1000-5862.2021.04.09]
　YU Xiaofeng,MA Yifan,LUO Zhaosheng,et al.The Attribute Hierarchical Structure Learning Based on K2 Algorithm[J].Journal of Jiangxi Normal University:Natural Science Edition,2021,(04):376-383.[doi:10.16357/j.cnki.issn1000-5862.2021.04.09]
点击复制

基于K2算法的属性层级结构学习研究()
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:
2021年04期
页码:
376-383
栏目:
心理与教育测量
出版日期:
2021-08-10

文章信息/Info

Title:
The Attribute Hierarchical Structure Learning Based on K2 Algorithm
文章编号:
1000-5862(2021)04-0376-08
作者:
喻晓锋1; 马奕帆1; 罗照盛1; 秦春影2
1.江西师范大学心理学院,江西 南昌 330022; 2.南昌师范学院数学与计算机系,江西 南昌 330032
Author(s):
YU Xiaofeng1; MA Yifan1; LUO Zhaosheng1; QIN Chunying2
1.School of Psychology,Jiangxi Normal University,Nanchang Jiangxi 330022,China; 2.Department of Mathematics and Computer Science,Nanchang Normal University,Nanchang Jiangxi 330032,China
关键词:
贝叶斯网络结构学习算法;  属性层级结构;  K2算法
Keywords:
Bayesian network structure learning algorithm;  attribute hierarchical structure;  K2 algorithm
分类号:
B 841
DOI:
10.16357/j.cnki.issn1000-5862.2021.04.09
文献标志码:
A
摘要:
诊断测验所考察的属性之间往往存在某种层级关系,然而基于专家经验获得的属性层级关系易出现分歧或错误.该文将属性掌握模式作为输入,考察K2算法在不同阈值条件下学习得到属性层级结构的准确性.模拟研究和实证数据分析的结果表明:K2算法对属性层级结构的学习有较高的成功率,并且K2算法对于4种基本层级结构有不同的敏感性,其中线性型和发散型对阈值的敏感性较低,而收敛型和无结构型对于阈值的敏感性较高.
Abstract:
There is often some hierarchical relationship among the attributes measured by the diagnostic test,but attribute hierarchical relationships are often difficult to obtain.Experience-based attribute-relationships are prone to errors.The attribute mastering model is taken as input,and the accuracy of the attribute hierarchical structure learned by the K2 algorithm under different conditions is evaluated.Simulation research and empirical data analysis results show that the K2 algorithm has a high accuracy rate for the learning of the attribute hierarchy,and the K2 algorithm has different sensitivities to the four basic hierarchical structures,among which the linear and divergent types are sensitive to the threshold,while the convergence type and unstructured type have higher sensitivity to the threshold.

参考文献/References:

[1] 罗照盛.认知诊断评价理论基础 [M].北京:北京师范大学出版社,2019.
[2] Leighton J,Gierl M.Cognitive diagnostic assessment for education:theory and applications [M].Cambridge:Cambridge University Press,2007.
[3] Templin J,Henson R A.Diagnostic measurement:theory,methods,and applications [M].Guilford:Guilford Press,2010.
[4] von Davier M,Lee Y S.Handbook of diagnostic classification models [M].Cham:Springer International Publishing,2019.
[5] Leighton J P,Gierl M J,Hunka S M.The attribute hierarchy method for cognitive assessment:a variation on Tatsuoka's rule:space approach [J].Journal of Educational Measurement,2004,41(3):205-237.
[6] 王晓庆,丁树良,罗芬.认知诊断中的Q矩阵及其作用 [J].心理科学,2019,42(3):739-746.
[7] Tatsuoka K K.Architecture of knowledge structures and cognitive diagnosis:a statistical pattern recognition and classification approach [EB/OL].[2020-03-19].https://psycnet.apa.org/record/1995-97594-013.
[8] 涂冬波,蔡艳,戴海琦.几种常用非补偿型认知诊断模型的比较与选用:基于属性层级关系的考量 [J].心理学报,2013,45(2):243-252.
[9] Liu Ren,Huggins M A C,Bradshaw L.The impact of Q-matrix designs on diagnostic classification accuracy in the presence of attribute hierarchies [J].Educational and Psychological Measurement,2017,77(2):220-240.
[10] 丁树良,罗芬.由偏序关系的可达阵导出Hasse图的有效算法:兼谈其在认知诊断中的作用 [J].江西师范大学学报:自然科学版,2013,37(5):441-444.
[11] Templin J,Bradshaw L.Hierarchical diagnostic classification models:a family of models for estimating and testing attribute hierarchies [J].Psychometrika,2014,79(2):317-339.
[12] Xu Gongjun,Shang Zhuoran.Identifying latent structures in restricted latent class models [J].Journal of the American Statistical Association,2018,113(523):1284-1295.
[13] Wang Chun,Lu Jing.Learning attribute hierarchies from data:two exploratory approaches [J].Journal of Educational and Behavioral Statistics,2020,46(1):58-84.
[14] Hu Bo,Templin J.Using diagnostic classification models to validate attribute hierarchies and evaluate model fit in Bayesian networks [J].Multivariate Behavioral Research,2020,55(2):300-311.
[15] 喻晓锋,丁树良,秦春影,等.贝叶斯网在认知诊断属性层级结构确定中的应用 [J].心理学报,2011,43(3):338-346.
[16] Pearl J.On evidential reasoning in a hierarchy of hypotheses [J].Artificial Intelligence,1986,28(1):9-15.
[17] Cooper G F,Herskovits E.A Bayesian method for the induction of probabilistic networks from data [J].Machine Learning,1992,9(4):309-347.
[18] Yu Xiaofeng,Cheng Ying.Data-driven Q-matrix validation using a residual:based statistic in cognitive diagnostic assessment [J].British Journal of Mathematical and Statistical Psychology,2020,73(S1):145-179.
[19] Heller J,Wickelmaier F.Minimum discrepancy estimation in probabilistic knowledge structures [J].Electronic Notes in Discrete Mathematics,2013,42:49-56.
[20] Philipp M,Strobl C,de la Torre J,et al.On the estimation of standard errors in cognitive diagnosis models [J].Journal of Educational and Behavioral Statistics,2018,43(1):88-115.

相似文献/References:

[1]詹沛达,丁树良,王立君.多分属性层级结构下引入逻辑约束的理想掌握模式[J].江西师范大学学报(自然科学版),2017,(03):289.
　ZHAN Peida,DING Shuliang,WANG Lijun.The Ideal Mastery Pattern for Polytomous Attributes with Hierarchical Structure Incorporating Mastery Level Restriction[J].Journal of Jiangxi Normal University:Natural Science Edition,2017,(04):289.

备注/Memo

备注/Memo:
收稿日期:2020-09-21
基金项目:国家自然科学基金(31660279,31600909),教育部人文社会科学研究(17YJC190029),江西省高等学校教学改革研究(JXJG-19-2-13,JXJG-19-23-2),江西省教育厅科学技术研究(GJJ191691,GJJ191128)和江西省教育厅人文社科课题(XL20202)资助项目.
作者简介:喻晓锋(1980—),男,安徽太湖人,副教授,博士,主要从事心理统计与测量方面的研究.E-mail:xyu6@jxnu.edu.cn
更新日期/Last Update: 2021-08-10