s'authentifier
version française rss feed
HAL : hal-00660045, version 1

Fiche détaillée  Récupérer au format
Computational Statistics (2011) Online First
Copula analysis of mixture models
Mathieu Vrac 1, Lynne Billard 2, Edwin Diday 3, Alain Chédin 4
(28/06/2011)

Contemporary computers collect databases that can be too large for classical methods to handle. The present work takes data whose observations are distribution functions (rather than the single numerical point value of classical data) and presents a computational statistical approach of a new methodology to group the distributions into classes. The clustering method links the searched partition to the decomposition of mixture densities, through the notions of a function of distributions and of multi-dimensional copulas. The new clustering technique is illustrated by ascertaining distinct temperature and humidity regions for a global climate dataset and shows that the results compare favorably with those obtained from the standard EM algorithm method.
1 :  Laboratoire des Sciences du Climat et de l'Environnement [Gif-sur-Yvette] (LSCE - UMR 8212)
CNRS : UMR8212 – CEA : DSM/LSCE – Université de Versailles Saint-Quentin-en-Yvelines (UVSQ)
2 :  Department of Statistics
University of Georgia
3 :  CEntre de REcherches en MAthématiques de la DEcision (CEREMADE)
CNRS : UMR7534 – Université Paris IX - Paris Dauphine
4 :  Laboratoire de Météorologie Dynamique (LMD)
CNRS : UMR8539 – INSU – Université Pierre et Marie Curie (UPMC) - Paris VI – Polytechnique - X – École normale supérieure [ENS] - Paris
Laboratoire de Meteorologie, Dynamique/IPSL, Ecole Polytechnique, 91128 Palaiseau, France
Mathématiques/Statistiques

Statistiques/Théorie
Classification of distributions – Copulas – Dynamical clustering – Data distributions – Estimation – Mixture model
Liste des fichiers attachés à ce document : 
PDF
Original_1_envoyA_pour_publication_vrac-CStatSept2510-AllBlack.pdf(1.8 MB)