Parsimonious modelling for mixtures of t-factor analyzers

碩士 === 國立中興大學 === 統計學研究所 === 98 === This paper presents a new class of parsimonious t mixture models, which is closely related to the family of mixture of t-factor analyzers. In particular, these models provide a unified framework for robust mixture modelling and clustering of high dimensional d...

Full description

Bibliographic Details
Main Authors: Shih-Hsuan Tsai, 蔡詩璇
Other Authors: Tsung-I Lin
Format: Others
Language:en_US
Published: 2010
Online Access:http://ndltd.ncl.edu.tw/handle/11722129248446900028