我们的网站为什么显示成这样？

可能因为您的浏览器不支持样式，您可以更新您的浏览器到最新版本，以获取对此功能的支持，访问下面的网站，获取关于浏览器的信息：

|本期目录/Table of Contents|

 针对微测评理念的自适应测验技术——基于CO-MIRT诊断模型(PDF)

《心理学探新》[ISSN:1003-5184/CN:36-1228/B]

期数:
 2021年05期
页码:
 458-465
栏目:
 
出版日期:
 2021-12-25

文章信息/Info

Title:
 Adaptive Testing Technology for Micro-testing Concept——Based on CO-MIRT Diagnosis Model
文章编号:
1003-5184(2021)05-0458-08
作者:
 孙雄飞1; 王永明2; 贾小君1
 (1.北京学格科技有限公司测评研发部,北京 100031; 2.英国伦敦国王学院,精神病学、心理学和神经科学研究所,伦敦)
Author(s):
 Sun Xiongfei1; Wang Yongming2; Jia Xiaojun1
 (1.Evaluation R&D Department,Beijing Xuege Technology Co.,Ltd,Beijing 100031; 2.Institute of Psychiatry,Psychology & Neuroscience,King’s College London,London)
关键词:
 微测评;  自适应测验;  多维能力参数;  CO-MIRT模型
Keywords:
 micro-evaluation;  adaptive testing;  multi-dimensional ability parameters;  CO-MIRT model
分类号:
 B841.2
DOI:
 -
文献标识码:
 A
摘要:
 前人研究业已表明MIRT模型在自适应测验等诸多领域的测量优势,但面对当前国内教育行业在实践过程中的现状,仍无法有效地解决待测知识点数量、试题数量和测量精度之间的矛盾。对此,本次研究设计了CO-MIRT模型,经由前馈层、全连接层的操作以共享试题之间所传递的信息,以及通过控制层、L2正则化等操作来限制小样本测验下的过拟合,来达到降低估计误差的目的。本次研究采用蒙特卡洛模拟的方式验证了模型效果,并使用数学推演的方式给予理论上的证明。
Abstract:
 Previous studies have shown the measurement advantages of the Multiple Item Response Theory(MIRT)model in many fields such as adaptive testing.However,in the face of the current status of the domestic education industry in the process of practice,it is still unable to effectively solve the problem contradiction.In this regard,this study designed the Cooperative Multiple Item Response Theory(CO-MIRT)model,through the feedforward layer and the fully connected layer to share the information passed between the test questions,and through the control layer,L2 regularization and other operations to limit the overfitting under the small sample test,and to reduce the estimation error.The Monte Carlo simulation was used to verify the model effect,and the mathematical deduction was used to give theoretical proof in our study.

参考文献/References

 蔡志煌.(2000).利用神经网络于题目反应理论参数估计之研究(硕士学位论文).台南师范学院,台湾.
黄坤泉.(2000).题目反应理论参数自动化估计之研究(硕士学位论文).台南师范学院,台湾.
余嘉元.(2002).基于联结主义的连续记分irt模型的项目参数和被试能力估计.心理学报,(5),80-86.
谭云兰,丁树良,辛锐铭.(2004).基于irt模型的bp神经网络降维法参数估计及其应用.江西师范大学学报(自然科学版),28(6),4.
余嘉元.(2009).基于神经网络集成的irt参数估计.江南大学学报(自然科学版),8(5),4.
郑海东.(1999).以类神经网络进行适性测验题目参数估计之研究(硕士学位论文).台南师范学院,台湾.
De,L.,& Song,H.(2009).Simultaneous estimation of overall and domain abilities:A higher-order irt model approach.Applied Psychological Measurement,33(8),620-639.
Golay,P.,& Lecerf,T.(2011).Orthogonal higher order structure and confirmatory factor analysis of the french wechsler adult intelligence scale(wais-iii).Psychological Assessment,23(1),143-152.
Huang,H.Y.,Chen,P.H.,& Wang,W.C.(2012).Computerized adaptive testing using a class of high-order item response theory models. Applied Psychological Measurement,36(8),689-706.
Huang,H.Y.,& Wang,W.C.(2013).Higher order testlet response models for hierarchical latent traits and testlet-based items.Educational & Psychological Measurement,73(3),491-511.
Jimmy,D.,& Hong,Y.(2010).Parameter estimation with small sample size a higher-order irt model approach.Applied Psychological Measurement,34(4),267-285.
Mislevy,R.J.,& Wingersky,S.M.(1993).How to equate tests with little or no data.Journal of Educational Measurement,30(1),55-78.
Reckase,M,D.(2009).Multidimensional item response theory.Springer New York.
Wang,F.,Liu,Q.,Chen,E.,Huang,Z.,& Wang,S.(2020).Neural cognitive diagnosis for intelligent education systems.Proceedings of the AAAT Conference on Artificial Intelligence,34(4),6153-6161.
Wang,C.,Kohli,N.,& Henn,L.(2015).A second-order longitudinal model for binary outcomes:Item response theory versus structural equation modeling.Structural Equation Modeling:A Multidisciplinary Journal,23(3).
Yeung,C.K.(2019).Deep-irt:Make deep learning based knowledge tracing explainable using item response theory.,23(3).
Yeung,C.K.(2019).iv e-prints.

备注/Memo

备注/Memo:
 通讯作者:孙雄飞,E-mail:442337729@qq.com。
更新日期/Last Update:  1900-01-01