期刊文献+

重尾数据的混合Erlang分布拟合方法

Mixed-Erlang Distribution Fitting for Heavy-tailed Data
下载PDF
导出
摘要 PH分布具有良好的解析性质,重尾数据的PH近似是随机模型分析中的重要课题。混合Erlang分布是一种常见的PH分布,本文利用EM方法给出了重尾数据的混合Erlang分布拟合算法,通过Matlab软件对两类常见重尾数据进行实验,结果令人满意。最后,文章对混合Erlang分布拟合算法的进一步改进做了总结。 Phase distribution has remarkable analytic properties, so Ph-approximation for heavy-tailed data is an important topic in the area of stochastic model analysis. Mixed-Erlang distribution is a familiar probability distribution. With EM algorithm, a fitting method for heavy-tailed data is introduced in this article. Matlab experi- ments on two kinds of heavy-tailed data indicate that the fitting is good. Finally, the article summarizes the further improvement for the Mixed-Erlang distribution algorithm.
出处 《运筹与管理》 CSSCI CSCD 北大核心 2013年第1期93-96,共4页 Operations Research and Management Science
基金 河南省教育厅自然科学研究计划项目(2011C110002) 新乡学院科技创新基金(201124) 河南省高等学校青年骨干教师资助计划项目(2011195)
关键词 PH分布 混合Erlang分布 EM算法 程序实现 phase distribution mixed-erlang distribution EM algorithm program realization
  • 相关文献

参考文献11

  • 1Garrett M W, Willinger W. Analysis, modeling and generation of self-similar video traffic [ J]. Proceedings of the ACM SIGCOMM' 94, London, UK, 1994 : 269-280.
  • 2Horvath A, Telek M. Approximating heavy tailed behavior with phase type distribution[ C ]. //Proceedings of the 3rd Interna- tional Conference on Matrix-Analytic Methods in Stochastic Models, Leuven, Belgium, 2000. 191-214.
  • 3Asmussen S. Applied probability and queues[ M]. Second Edition, Springer, 2003: 84-85.
  • 4Bobbio A, Horvath A, Telek M. Matching three moments with minimal acyclic phase type distributions[ J]. Stochastic Mod- els, 2005, 21(223) : 303-326.
  • 5Johnson M A, Taaffe M R. Matching moments to phase distributions: nonlinear programming approaches[ J]. Communications in Statistics -Stochastic Models, 1990, 7(6) : 259-281.
  • 6Johnson M A. Selecting parameters of phase distributions: combining nonlinear programming, heuristics, and Erlang distribu- tions[J]. ORSA Journal on Computing, 1993 , 5( 1 ) : 69-83.
  • 7Harris C M, Marchal W G. Distribution estimation using Laplace transforms[J]. Informs Journal on computing, 1998, 10 (4) : 448-458.
  • 8Dempster A P, Laird N M, Rubin D B. Maximum likelihood from incomplete data via the EM algorithm[J]. Journal of the Royal Statistical Society, 1977, (39) : 1-38.
  • 9Asmussen S, Nerman O, Olsson M. Fitting phase-type distributions via the EM algorithm [ J]. Scandinavian Journal of Statis- tics, 1996, 23(4): 419-441.
  • 10Thumer A, Buchholz P, Telek M. A novel approach for phase-type fitting with the EM algorithm[ J]. IEEE Transactions on Dependable and Secure Computing, 2006, 3 (3) : 245-258.

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