期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

改进3PL模型参数估计的MCMC算法 被引量：1

MCMC Algorithm of the Parameter-estimation Method Under the Improved Three-Parameter Logistic Model
原文传递
导出
摘要 本文首先用马尔科夫链蒙特卡洛(MCMC)算法和EM算法进行IRT模型参数估计模拟实验,并探讨了两种算法的参数估计精度,然后在分析三参数Logistic(3PL)模型参数估计精度的基础上改进模型并对其进行参数估计。结果表明,MCMC算法估计IRT模型的参数精度均优于EM算法,并且MCMC算法在估计3PL模型参数方面具有更明显的优势;在样本量较小的情况下,MCMC算法能较好地估计3PL模型参数,估计精度略低于2PL模型;3PL模型的项目参数确定性低是参数估计精度略低于2PL模型的主要原因;采用改进模型可以提高项目参数的确定性,进而得到更优的参数估计精度。 Simulation experiments on the parameter estimation of the item response theory（IRT） model were carried out with markov chain monte Carlo（MCMC） algorithm.Then the veracity of the parameter estimation with MCMC algorithm was compared with EM algorithm,the reason why the veracity of the parameter estimation of the 3PL model was worse was investigated,and the improvement of the 3PL model was tried out.The veracity of parameter estimation with MCMC algorithm was found to be better than that with EM algorithm.The MCMC algorithm was also effective in estimating the parameters of the 3PL model,even if the veracity of the parameter estimation of the 3PL model was not as high as that of the 2PL model.The key reason for the worse veracity of the parameter estimation of the 3PL model was the poor identifiability of its item parameters.The Improved - 3PL model could increase the distinguishability of item parameters,and then the veracity of its item parameters estimation was ter than standard 3PL model.
作者 甘媛源 余嘉元
机构地区 南京师范大学心理系
出处 《心理科学》 CSSCI CSCD 北大核心 2010年第5期1212-1215,共4页 Journal of Psychological Science
基金 国家社科基金"十一五"规划课题(BBA080050) 江苏省教育科学"十一五"规划课题(D/2008/01/105)项目资助
关键词 马尔科夫链蒙特卡洛 双参数Logistic模型 三参数Logistic模型 确定性 markov chain monte carlo two parameter logistic model three parameter logistic model identifiability
分类号 B841 [哲学宗教—基础心理学]
  • 相关文献

参考文献9

  • 1王权.“马尔可夫链蒙特卡洛”(MCMC)方法在估计IRT模型参数中的应用[J].考试研究,2006,2(4):45-63. 被引量：14
  • 2Yao L. , Richard D. , Schwarz. A multidimensional partial credit model with associated item and test statistics: an application to mixed format tests [J]. Applied Psychological Measurement, 2006, 30(6): 469-492.
  • 3Andre A. R. , Bruno D. Z. Understanding parameter invariance in unidimensional IRT models [J]. Educational and Psychological Measurement, 2006, 66(1) : 63 - 84.
  • 4Liu Y. , Schulz M E. , Yu L. Standard error estimation of 3PL IRT true score equating with an MCMC Method [J]. Journal of Educational and Behavioral Statistics, 2007, 32(4): 1 -22.
  • 5Albert J H. Bayesian estimation of normal ogive item response curves using Gibbs sampling [J]. Journal of Educational Statistics, 1992(17): 251-269.
  • 6Patz R J, Junker B W. A straightforward approach to markov chain monte carlo met_hods for item response models [J]. Journal of Educational and Behavioral Statistics, 1999, 24(2): 146-178.
  • 7涂冬波,漆书青,蔡艳,戴海琦,丁树良.IRT模型参数估计的新方法--MCMC算法[J].心理科学,2008,31(1):177-180. 被引量：18
  • 8Junker B W, Patz R J. Applications and extensions of MCMC in JRT: Multiple item types, missing data, and rated responses [J]. Journal of Educational and Behavioral Statistics, 1999, 24(4) : 342-366.
  • 9Tsutakawa R K. Prior distributions for item response curves [J ]. British Journal of Mathematical and Statistical Psychology. 1992, 45(1): 51 -74.

二级参考文献12

  • 1Albert J H. Bayesian estimation of normal ogive item response curves using Gibbs sampling. Journal of Educational Statistics, 1992, (17):251- 269
  • 2Richard Patz J, Brian Junker W. A straightforward approach to Markov Chain Monte Carlo Methods for Item Response Models, Journal of Educational and Behaviorial Statistics, 1999, 24(2):146- 178
  • 3Richard Patz J, Brian Junker W. Application and Extensions of MCMC in IRT: Multipe Item Types, Missing Data, and Rated Responses. Journal of Educational and Behaviorial Statistics, 1999, 24(4) :342 - 366
  • 4Bradlow E T, Wainer H, Wang X. A Bayesian random effects model for testlets. Psychometrika, 1999, 64:153 - 168
  • 5Wainer H, Bradlow E T., Du Z. Testlet response theory:An analog for the 3PL model useful in adaptive testing. In: Van der Linden W J, Glas C A W. (Eds.). Computerized adaptive testing: Theory and practice. Boston, MA: Kluwer - Nijhoff, 2001 : 245 - 270
  • 6Hatz S M, Rousson L, Stout W. Skills diagnosis: Theory and practice(Technical Report). Princeton, NJ : Educational Testing Service
  • 7Jimmy D T, Douglas J A. Higher - order latenf trait models for cognitive diagnosis. Psychometrika, 2004, 69(3) : 333 - 353
  • 8Jiang Yanlin. Estimating parameters for multidimensional item response theory models by MCMC methods (unpublished doctoral dissertation). Michigan State University, 2005
  • 9Gentle J E. Elements of Computational Statistics. Science Press, 2006 : 39 - 66
  • 10龚光鲁,钱敏平.应用随机过程教程.清华大学出版社,2003:191-202

共引文献24

同被引文献14

  • 1BEAUJEAN A A, STEVEN J O. Using item response theory to assess the flynn effect in the national Longitudinal study of youth 79 children and young[J]. Adults Ddata Intell, 2008,36(3) :455 - 463.
  • 2CHANG C H, REEVE B B. Item response theory and its applications to patient-reported outcomes measurement [J]. Eval Health Prof, 2005,28(3) :264 - 282.
  • 3BAKER F B, KIM S H. Item response theory: parameter Estimation Techniques[M]. 2nd Ed. New York: Marcel Dekker, 2004.
  • 4BOCK R D, AITKIN M. Marginal maximum likelihood estimation of item parameters: An application of an EM- algorithm[J]. Psychometrika, 1981,46(3) :443 - 459.
  • 5DAVIER M V, SINHARAY S. An importance sampling EM algorithm for latent regression models[J]. J Educ Behav Stat, 2007,32(3):233 - 251.
  • 6FIEUWS S. High dimensional multivariate mixed models for binary questionnaire data[J]. Appl Stat, 2006,55(4) : 449 - 460.
  • 7ALBERT J H. Bayesian estimation of normal ogive item response curves using Gibbs Sampling [J]. J Educ Stat, 1992,17 (3) : 251 - 269.
  • 8SAHU S K. Bayesian estimation and model choice in item response models[J]. J Stat Comput and Simul, 2002,72 (3) :217 - 232.
  • 9LINDEN V D. A hierarchical framework for modeling speed and accuracy on test items[J]. Psychometrika, 2007,72 (3) :287 - 308.
  • 10JANNEKE M. Application of multidimensional item response theory models to longitudinal data[J]. Educ Psycho Meas, 2006,66(1):5 - 34.

引证文献1

二级引证文献2

心理科学
2010年 第5期

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