CLASSIFICATION PROBLEMS OF SAMPLES OF FINITE MIXTURES OF COMPOSITIONS

被引：5

作者：

BARCELO, C

PAWLOWSKY, V

GRUNSKY, E

机构：

[1] UNIV POLITECN CATALUNYA,ETS ENGINYERS CAMINS CANALS & PORTS,DEPT MATEMAT APLICADA 3,E-08034 BARCELONA,SPAIN

[2] MINIST ENERGY MINES & PETR RESOURCES,GEOL SURVEY BRANCH,VICTORIA,BC V8V 1X4,CANADA

来源：

MATHEMATICAL GEOLOGY | 1995年 / 27卷 / 01期

关键词：

DISCRIMINANT ANALYSIS; COMPOSITIONAL DATA; MIXTURE MODELS;

D O I：

10.1007/BF02083571

中图分类号：

P [天文学、地球科学];

学科分类号：

07 ;

摘要：

A discriminant technique based on mixture models is presented to be applied when observations are a sample of a mixture of compositions with each component following an additive logistic normal distribution on the d-dimensional simplex. The efficiency of this discriminant technique is compared empirically with the efficiency of the standard discriminant technique based on logcontrast. Simulated compositional data and a real dataset are used to carry out these comparisons.

引用

页码：129 / 148

页数：20

共 14 条

[1]

AITCHISON J, 1986, STATISTICAL ANAL COM

[2]

BARCELO C, 1994, SCI TERRE NANCY I, V32, P29

[3] MAXIMUM LIKELIHOOD FROM INCOMPLETE DATA VIA EM ALGORITHM [J].