期刊文献+

四参数Logistic模型与双参数、三参数Logistic模型在语言测验中的拟合比较及睡眠现象检验--以来华留学生预科结业考试为例 被引量:1

A Fitting Study of Four-Parameter Logistic Model with Two-and Three-Parameter Logistic Models and Sleeping Phenomenon Detection in Language Testing:A Case Study of Chinese Proficiency Test
下载PDF
导出
摘要 四参数Logistic模型通过引入第4个参数,分析测验中高能力被试答错低难度试题的睡眠现象。运用四参数Logistic模型与双参数、三参数Logistic模型对汉语作为第二语言测验的实测数据进行分析,比对3种模型的分析结果,并通过四参数Logistic模型分析测验中的睡眠现象,结果表明:在模型拟合方面,四参数Logistic模型表现良好;四参数Logistic模型对项目区分度的估计结果高于双参数、三参数Logistic模型;语言测验存在睡眠现象时,被试能力值可能会被严重低估,高风险考试需要考虑使用四参数Logistic模型进行矫正;在语言测验中,睡眠现象是一种随机的失误现象,与所测的语言技能无关。 The four-parameter logistic model was used to analyze the sleeping phenomenon in which examinees with high ability accidentally give wrong responses to questions they should have answered correctly.In this study,the four-parameter logistic model was compared with the two-parameter and three parameter logistic models to analyze the actual data of the Chinese as a second language testing,and the four parameter logistic model was used to analyze the sleeping phenomenon in the test.The results showed that:the four-parameter logistic model performed well in terms of model fit;the four-parameter logistic model estimated item discrimination better than the two and three-parameter logistic models;the presence of the sleeping phenomenon in language tests may cause serious underestimation of the examinees’ability values,and the four-parameter logistic model needs to be considered for correction in high-stakes tests;the sleeping phenomenon is a random error phenomenon in language testing and is not related to the part of the test.
作者 金英姿 王佶旻 JIN Yingzi;WANG Jimin(Beijing Language and Culture University,Beijing 100083,China)
出处 《中国考试》 CSSCI 北大核心 2022年第8期57-65,共9页 journal of China Examinations
关键词 四参数Logistic模型 项目反应理论 睡眠现象 语言测验 four-parameter logistic model item response theory sleeping phenomenon language testing
  • 相关文献

参考文献5

二级参考文献25

  • 1TIAN Maozai & CHEN Gemai School of Statistics, Renmin University of China, Beijing 100872, China and Center for Applied Statistics, Renmin University of China, Beijing 100872, China,Department of Mathematics and Statistics, University of Calgary, Canada.Hierarchical linear regression models for conditional quantiles[J].Science China Mathematics,2006,49(12):1800-1815. 被引量:20
  • 2戴海崎,简小珠.被试作答的偶然性对IRT能力估计的影响研究[J].心理科学,2005,28(6):1433-1436. 被引量:6
  • 3吴德福.四参数Logistic函数的简化求解[J].中华核医学杂志,1990,10:48-48.
  • 4简小珠,戴海崎,彭春妹.IRT中Logistic模型的c、γ参数对能力估计的改善[J].心理学报,2007,39(4):737-746. 被引量:6
  • 5Wright B D.Solving measurement problems with the research model.Journal of Educational Measurement,1977,14:97-116.
  • 6Reise S P,Waller N G.How many IRT parameters does it take to model psychopathology items?Psychological Methods,2003,8(2):164-184.
  • 7Hessen D J.A new class of parametric IRT models for dichotomous item scores.Journal of Applied Measurement,2004,5(4):385-397.
  • 8McDonald R P.Non-linear factor analysis.Psychometric Monographs,1967:15.
  • 9Barton M A,Lord F M.An upper asymptote for the three-parameter Logistic item response model.In:Research Bulletin.Princeton,NJ:Educational Testing Service,1981:81-20.
  • 10Hambleton R K,Swaminathan H.Item response theory:Principles and applications.Boston:Kluwer-Nijhoff,1985:48-49.

共引文献20

同被引文献11

引证文献1

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部