A novel mixture model using the multivariate normal mean-variance mixture of Birnbaum-Saunders distributions and its application to extrasolar planets

JOURNAL OF MULTIVARIATE ANALYSIS

卷:171

Article

Naderi, Mehrdad¹  Hung, Wen-Liang^2,3  Lin, Tsung-I^4,5  Jamalizadeh, Ahad^6,7 

[1] Univ Pretoria, Fac Nat & Agr Sci, Dept Stat, Pretoria, South Africa

[2] Natl Tsing Hua Univ, Ctr Teacher Educ, Hsinchu, Taiwan

[3] Natl Tsing Hua Univ, Dept Comp Sci, Hsinchu, Taiwan

[4] Natl Chung Hsing Univ, Inst Stat, Taichung 402, Taiwan

[5] China Med Univ, Dept Publ Hlth, Taichung 404, Taiwan

[6] Shahid Bahonar Univ Kerman, Fac Math & Comp, Dept Stat, Kerman, Iran

[7] Shahid Bahonar Univ Kerman, Mahani Math Res Ctr, Kerman, Iran

关键词: Birnbaum-Saunders distribution;    EM algorithm;    GH distribution;    Normal mean-variance mixture;   

DOI  :  10.1016/j.jmva.2018.11.015

来源: Elsevier

【 摘 要 】

This paper presents a new finite mixture model based on the multivariate normal mean variance mixture of Birnbaum-Saunders (NMVBS) distribution. We develop a computationally analytical EM algorithm for model fitting. Due to the dependence of this algorithm on initial values and the number of mixing components, a learning-based EM algorithm and an extended variant are proposed. Numerical simulations show that the proposed algorithms allow for better clustering performance and classification accuracy than some competing approaches. The effectiveness and prominence of the proposed methodology are also shown through an application to an extrasolar planet dataset. (C) 2018 Elsevier Inc. All rights reserved.

【 授权许可】

Free