[1]熊建华,罗 慧,王晓庆,等.基于GRM的在线校准研究[J].江西师范大学学报(自然科学版),2018,(01):62-66.[doi:10.16357/j.cnki.issn1000-5862.2018.01.11]
　XIONG Jianhua,LUO Hui,WANG Xiaoqing,et al.The Online Calibration Based on Graded Response Model[J].Journal of Jiangxi Normal University:Natural Science Edition,2018,(01):62-66.[doi:10.16357/j.cnki.issn1000-5862.2018.01.11]
点击复制

基于GRM的在线校准研究()
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:
2018年01期
页码:
62-66
栏目:
心理与教育测量
出版日期:
2018-02-20

文章信息/Info

Title:
The Online Calibration Based on Graded Response Model
文章编号:
1000-5862(2018)01-0062-05
作者:
熊建华; 罗 慧; 王晓庆; 丁树良
江西师范大学计算机信息工程学院,江西 南昌 330022
Author(s):
XIONG Jianhua; LUO Hui; WANG Xiaoqing; DING Shuliang
College of Computer Information Engineering,Jiangxi Normal University,Nanchang Jiangxi 330022,China
关键词:
在线校准;  夹逼平均法;  多步EM算法;  多序列相关系数法
Keywords:
online calibration;  squeezing average method;  the multiple EM cycle method;  multiple-sequence correlation coefficient method
分类号:
B 841.7
DOI:
10.16357/j.cnki.issn1000-5862.2018.01.11
文献标志码:
A
摘要:
计算机化自适应测验的题库面临建设成本高且更新、扩充技术较复杂等问题.在线校准技术,可以将新题和旧题置于同一参数量尺上,降低了题库扩充成本.已有若干关于两级评分下新题的在线校准研究,但多级记分项目的在线校准却鲜见报道.该文先由拓展的夹逼平均法求取难度初值,并用多序列相关系数法求取区分度初值,再采用多步EM算法估计项目参数.Monte Carlo模拟结果表明:新题项目参数的估计值返真性较好,且参数的估计精度随着作答次数的小幅度增加而保持着逐渐提高的趋势.
Abstract:
Item bank of computerized adaptive test is faced with high construction cost and updated,expanded technology more complex.Not only can the application of the online calibration technology reduce cost,but also put the calibrated parameter values of the new items and the old in the same scale.Online calibration of new items under dichotomously scored models has achieved good results,but under polytomously scored items is reported rarely.To explore the performance of online calibration for polytomously scored items,a method to calculate the initial values of the multiple EM cycle method(MEM)is proposed based on graded response model(GRM),which is focus on the extended squeezing average method and the multiple-sequence correlation coefficient method to calculate as the initial parameters of the new item,then use the multiple EM cycle method to estimate parameters.Results of Monte Carlo simulation show that the parameter estimation of new items can get acceptable estimation accuracy and the parameters of new items are more accurate with a small increase of the sample size for calibration.

参考文献/References:

[1] Wainer H,Mislevy R J,Wainer H,et al.Item response theory,item calibration,and proficiency estimation [J].Bioresource Technology,1990,98(1):218-20.
[2] 陈平,张佳慧,辛涛.在线标定技术在计算机化自适应测验中的应用 [J].心理科学进展,2013,21(10):1883-1892.
[3] 陈平.2种新的计算机化自适应测验在线标定方法 [J].心理学报,2016,48(9):1184-1198.
[4] He Yinhong,Chen Ping,Li Yong,et al.A new online calibration method based on Lord's Bias-correction(online first)[J].Applied Psychological Measurement,2017,41(6):456-471.
[5] 汪文义.认知诊断评估中项目属性辅助标定方法研究 [D].南昌:江西师范大学,2012.
[6] 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.
[7] 游晓锋,丁树良,刘红云.计算机化自适应测验中原始题项目参数的估计 [J].心理学报,2010,42(7):813-820.
[8] Zheng Yi.Online calibration of polytomous items under the generalized partial credit model [J].Applied Psychological Measurement,2016,40(6):434-450.
[9] Samejima F.Estimation of latent ability using a response pattern of graded scores [J].Psychometrika,1969,34(1):1-97.
[10] Ban J C,Hanson B A,Wang T,et al.A comparative study of on-line pretest item: calibration/scaling methods in computerized adaptive testing [J].Journal of Educational Measurement,2001,38(3):191-212.
[11] 漆书青.现代教育与心理测量学原理 [M].北京:高等教育出版社,2002.
[12] 张厚粲,徐建平.现代心理与教育统计学 [M].北京:北京师范大学出版社,2004.
[13] 陈青,丁树良,朱隆尹,等.3参数等级反应模型及其参数估计 [J].江西师范大学学报:自然科学版,2010,34(2):117-122.

备注/Memo

备注/Memo:
收稿日期:2017-10-12
基金项目:汉考国际科研基金项目“基于GRM的项目参数在线校准”(CTI2017B06)的研究成果.
作者简介:熊建华(1977-),女,江西樟树人,副教授,主要从事智能教育软件的研究.E-mail:270281168@qq.com
更新日期/Last Update: 2018-02-20