期刊文献+

DIF比例与纯化方式对LRDIF检测方法的影响研究

Effects of DIF Proportion and Purification Type on Robustness and Power of LRDIF Procedure
下载PDF
导出
摘要 本模拟研究的目标组与参照组的项目作答反应数据是通过Rasch模型产生的,模拟研究探讨了LRDIF检测方法在不同DIF比例和纯化方式下的检测效果。研究结果表明:LRDIF方法的检测结果在DIF比例≤40%时是可信的;当采用LRDIF方法进行DIF检测时,有必要对匹配变量进行纯化,最好是能够进行迭代纯化。 In this simulation study, the detection effects of LRDIF procedure under conditions of various DIF proportions and purification types were studied. The results show that: it is reliable to use LRDIF procedure to detect DIF when DIF proportion is not more than 40% ; when using LRDIF procedure, it is necessary to purify matching variable and it is best to conduct iterative purification.
作者 朱乙艺
出处 《考试研究》 2014年第2期54-58,共5页 Examinations Research
关键词 DIF比例 纯化方式 LRDIF方法 项目功能差异 DIF Proportion, Purification Type, LRDIF Procedure, Differential Item Functioning
  • 相关文献

参考文献5

  • 1Bradley, J. V. Robustness? [ J ]. The British Journal of Mathematical & Statistical Psychology, 1978, 31 : 144 - 152.
  • 2Cohen, J. (2nd Ed. ) Statistical Power Analysis for the Behavioral Sciences [M]. Hillsdale, NJ: Erlbaum, 1988.
  • 3Hariharan Swaminathan, H. & Jane Rogers. Detecting Differential Item Functioning Using Logistic Regression Procedures [ J ]. Journal of Educational Measurement, 1990, (4) : 361 - 370.
  • 4ANgel M. , Fidalgo, Gideon J. & Mellenbergh, JosE Mu H iz.Effects of Amount of DIF, Test Length, and Purification Type on Robustness and Power of Mantel-Haenszel Procedures [ J ]. Methods of Psychological Research, 2000, (3) : 43 - 53.
  • 5Zumbo, B. D. A Handbook On The Theory and Methods of Differential Item Functioning (DIF) : Logistic Regression Modeling As A Unitary Framework For Binary and Likert-Type (Ordinal) Item Scores [ M ]. Ottawa, ON: Directorate of Human Resources Research and Evaluation, Department of National Defense, 1999.

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