Please use this identifier to cite or link to this item: http://hdl.handle.net/11455/37083
標題: Robust mixture modeling using multivariate skew t distributions
作者: Lin, T.I.
林宗儀
關鍵字: MCEM-type algorithms
MSN
MST
Multivariate truncated normal
Multivariate truncated t
Outliers
maximum-likelihood-estimation
em algorithm
density-estimation
unknown
number
components
inference
ecm
期刊/報告no:: Statistics and Computing, Volume 20, Issue 3, Page(s) 343-356.
摘要: This paper presents a robust mixture modeling framework using the multivariate skew t distributions, an extension of the multivariate Student's t family with additional shape parameters to regulate skewness. The proposed model results in a very complicated likelihood. Two variants of Monte Carlo EM algorithms are developed to carry out maximum likelihood estimation of mixture parameters. In addition, we offer a general information-based method for obtaining the asymptotic covariance matrix of maximum likelihood estimates. Some practical issues including the selection of starting values as well as the stopping criterion are also discussed. The proposed methodology is applied to a subset of the Australian Institute of Sport data for illustration.
URI: http://hdl.handle.net/11455/37083
ISSN: 0960-3174
文章連結: http://dx.doi.org/10.1007/s11222-009-9128-9
Appears in Collections:統計學研究所

文件中的檔案:

取得全文請前往華藝線上圖書館



Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.