Passer à la navigation principale Passer à la recherche Passer au contenu principal

On clustering procedures and nonparametric mixture estimation

  • Université du Littoral Côte d'Opale
  • Université de Strasbourg
  • ENSAE

Résultats de recherche: Contribution à un journal › Article › Revue par des pairs

2 Citations (Scopus)

Résumé

This paper deals with nonparametric estimation of conditional densities in mixture models in the case when additional covariates are avail- able. The proposed approach consists of performing a preliminary clustering algorithm on the additional covariates to guess the mixture component of each observation. Conditional densities of the mixture model are then es- timated using kernel density estimates applied separately to each cluster. We investigate the expected L1-error of the resulting estimates and derive optimal rates of convergence over classical nonparametric density classes provided the clustering method is accurate. Performances of clustering al- gorithms are measured by the maximal misclassification error. We obtain upper bounds of this quantity for a single linkage hierarchical clustering algorithm. Lastly, applications of the proposed method to mixture models involving electricity distribution data and simulated data are presented.

langue originaleAnglais
Pages (de - à)266-297
Nombre de pages32
journalElectronic Journal of Statistics
Volume9
Les DOIs
étatPublié - 1 janv. 2015
Modification externeOui

Empreinte digitale

Examiner les sujets de recherche de « On clustering procedures and nonparametric mixture estimation ». Ensemble, ils forment une empreinte digitale unique.

Contient cette citation