[1]康春花,孙小坚,顾士伟,等.多水平多维IRT模型在学业质量监测中的应用[J].江西师范大学学报(自然科学版),2016,40(02):140-144.
 KANG Chunhua,SUN Xiaojian,GU Shiwei,et al.The Application of Multilevel Multidimensional IRT Model in Academic Quality Monitoring Test[J].,2016,40(02):140-144.
点击复制

多水平多维IRT模型在学业质量监测中的应用()
分享到:

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

卷:
40
期数:
2016年02期
页码:
140-144
栏目:
出版日期:
2016-03-25

文章信息/Info

Title:
The Application of Multilevel Multidimensional IRT Model in Academic Quality Monitoring Test
作者:
康春花;孙小坚;顾士伟;曾平飞
浙江师范大学教师教育学院,浙江 金华 321004
Author(s):
KANG ChunhuaSUN XiaojianGU ShiweiZENG Pingfei
College of Teacher Education,Zhejiang Normal University,Jinhua Zhejiang 321004,China
关键词:
多水平多维IRT模型 学业能力 质量监测 父母受教育程度
Keywords:
multilevel multidimensional IRT model academic achievement quality monitoring education background of parents
分类号:
B 842.1
文献标志码:
A
摘要:
用多水平多维IRT(ML-MIRT)模型对学生学业情况进行分析,进而拓宽该模型的适用范围.首先采用不包含任何预测变量的零模型对项目参数和学生参数进行分析,然后使用包含学生预测变量的ML-MIRT模型分析2个预测变量对学生学业能力的影响.研究结果表明:试题的难度基本上贯穿了整个能力量尺,试题也具有较好的区分度,3个能力维度的跨级相关系数均达到了显著性水平,父亲的受教育程度对学生的3个能力维度均有显著影响,而母亲的受教育程度无显著影响.因此,编制的测验较为合理,ML-MIRT模型适用于监测学生学业水平,父亲的受教育程度对学生学业水平有着重要影响.
Abstract:
Analysis the academic achievement of students with multilevel multidimensional IRT(ML-MIRT)model,and expand the application field of the model.First,use the zero model,which does not contain any predictor,to analysis the item and person parameters; then use the ML-MIRT model that contains two predictors about students to explore the impact of the predictors on students' academic achievement.Difficulty of these items and the ability scale is matching,and most of items have good discrimination,the intraclass correlation coefficients(ICC)of the three abilities are significant,the education background of father affects the three abilities of students significantly,while the education background of mother doesn't affect them.The test is reasonable,and the ML-MIRT model is appropriate,also and the education background of father plays an important role for children's academic achievement.

参考文献/References:

[1] 刘慧,简小珠,张敏强,等.多水平 IRT 的发展与应用述评 [J].心理科学进展,2012,20(4):627-632.
[2] 刘红云,骆方.多水平项目反应理论模型在测验发展中的应用 [J].心理学报,2008,40(1):92-100.
[3] Bacci S,Caviezel V.Multilevel IRT models for the university teaching evaluation [J].Journal of Applied Statistics,2011,38(12):2775-2791.
[4] Fox J P,Glas C A.Bayesian estimation of a multilevel IRT model using Gibbs sampling [J].Psychometrika,2001,66(2):271-288.
[5] Fox J P.Applications of multilevel IRT modeling [J].School Effectiveness and School Improvement,2004,15(3/4):261-280.
[6] Hox J.Multilevel analysis:Techniques and applications [M].New York:Routledge Press,2010.
[7] 康春花,辛涛.测验理论的新发展:多维项目反应理论 [J].心理科学进展,2010(3):530-536.
[8] Höhler J,Hartig J,Goldhammer F.Modeling the multidimensional structure of students' foreign language competence within and between classrooms [J].Psychological Test and Assessment Modeling,2010,52(3):323-340.
[9] Hartig J,Höhler J.Representation of competencies in multidimensional IRT models with within-item and between-item multidimensionality [J].Zeitschrift für Psychologie/Journal of Psychology,2008,216(2):89-101.
[10] De Jong M G,Steenkamp J B E.Finite mixture multilevel multidimensional ordinal IRT models for large scale cross-cultural research [J].Psychometrika,2010,75(1):3-32.
[11] Lu Y,Bolt D M.Examining the attitude-achievement paradox in PISA using a multilevel multidimensional IRT model for extreme response style [J].Large-scale Assessments in Education,2015,3(1):1-18.
[12] Stout W.Skills diagnosis using IRT-based continuous latent trait models [J].Journal of Educational Measurement,2007,44(4):313-324.
[13] 涂冬波,蔡艳,戴海琦,等.多维项目反应理论:参数估计及其在心理测验中的应用 [J].心理学报,2011,43(11):1329-1340.
[14] Lahuis D M,Avis J M.Using multilevel random coefficient modeling to investigate rater effects in performance ratings [J].Organizational Research Methods,2007,10(1):97-107.
[15] Wang Wenchung,Qiu Xuelan.A multidimensional and multilevel extension of a random-effect approach to subjective judgment in rating scales [J].Multivariate Behavioral Research,2013,48(3):398-427.
[16] Melby J N,Conger R D,Fang S A,et al.Adolescent family experiences and educational attainment during early adulthood [J].Developmental Psychology,2008,44(6):1519.
[17] Fox J P.Bayesian item response modeling:theory and applications [M].Berlin:Springer Science & Business Media,2010.
[18] Ntzoufras I.Bayesian modeling using WinBUGS [M].Man hattan:John Wiley & Sons,2011.
[19] 温福星.阶层线性模型的原理与应用 [M].北京:中国轻工业出版社,2009.
[20] 邱皓政.量化研究法(二):统计原理与分析技术 [M].台北:双叶书廊图书公司,2005.
[21] Ermisch J,Pronzato C.Causal effects of parents' education on children's education [R].ISER Working Paper Series,2010.
[22] Crook C J.The role of mothers in the educational and status attainment of Australian men and women [J].Journal of Sociology,1995,31(2):45-73.
[23] 庞维国,徐晓波,林立甲,等.家庭社会经济地位与中学生学业成绩的关系研究 [J].全球教育展望,2013(2):12-21.
[24] 康春花,孙小坚,曾平飞.基于等级反应模型的多水平多侧面评分者模型 [J].心理科学,2016(1):214-223.

备注/Memo

备注/Memo:
基金项目:浙江省自然科学基金(LY15C090003)和教育部基础教育质量监测中心课题(2014AC001-D)资助项目.
更新日期/Last Update: 1900-01-01