Item


Log-ratio methods in mixture models for compositional data sets

When traditional methods are applied to compositional data misleading and incoherent results could be obtained. Finite mixtures of multivariate distributions are becoming increasingly important nowadays. In this paper, traditional strategies to fit a mixture model into compositional data sets are revisited and the major difficulties are detailed. A new proposal using a mixture of distributions defined on orthonormal log-ratio coordinates is introduced. A real data set analysis is presented to illustrate and compare the different methodologies

This research was supported by the Ministerio de Economía y Competividad through the projects “METRICS” and “CoDa-RETOS” (MTM2012-33236; MTM2015-65016- C2-1-R: MINECO/FEDER,UE) and the Agència de Gestió d’Ajuts Universitaris i de Recerca (AGAUR: 2014SGR551)

SORT : statistics and operations research transactions, 2016, vol. 40. núm 2, 349-374

Institut d’Estadística de Catalunya (Idescat)

Author: Comas Cufí, Marc
Martín Fernández, Josep Antoni
Mateu i Figueras, Glòria
Date: 2016
Abstract: When traditional methods are applied to compositional data misleading and incoherent results could be obtained. Finite mixtures of multivariate distributions are becoming increasingly important nowadays. In this paper, traditional strategies to fit a mixture model into compositional data sets are revisited and the major difficulties are detailed. A new proposal using a mixture of distributions defined on orthonormal log-ratio coordinates is introduced. A real data set analysis is presented to illustrate and compare the different methodologies
This research was supported by the Ministerio de Economía y Competividad through the projects “METRICS” and “CoDa-RETOS” (MTM2012-33236; MTM2015-65016- C2-1-R: MINECO/FEDER,UE) and the Agència de Gestió d’Ajuts Universitaris i de Recerca (AGAUR: 2014SGR551)
Format: application/pdf
ISSN: 1696-2281 (versió paper)
2013-8830 (versió electrònica)
Document access: http://hdl.handle.net/10256/13747
Language: eng
Publisher: Institut d’Estadística de Catalunya (Idescat)
Collection: MICINN/PN 2013-2015/MTM2012-33236
MINECO/PE 2016-2018/MTM2015-65016-C2-1-R
Reproducció digital del document publicat a: http://www.raco.cat/index.php/SORT/article/view/316149/406263
Articles publicats (D-IMA)
Is part of: SORT : statistics and operations research transactions, 2016, vol. 40. núm 2, 349-374
Rights: Attribution-NonCommercial-NoDerivs 3.0 Spain
Rights URI: http://creativecommons.org/licenses/by-nc-nd/3.0/es/
Subject: Anàlisi multivariable
Multivariate analysis
Title: Log-ratio methods in mixture models for compositional data sets
Type: info:eu-repo/semantics/article
Repository: DUGiDocs

Subjects

Authors