Non parametric finite translation mixtures with dependent regime

Abstract : In this paper we consider non parametric finite translation mixtures. We prove that all the parameters of the model are identifiable as soon as the matrix that defines the joint distribution of two consecutive latent variables is non singular and the translation parameters are distinct. Under this assumption, we provide a consistent estimator of the number of populations, of the translation parameters and of the distribution of two consecutive latent variables, which we prove to be asymptotically normally distributed under mild dependency assumptions. We propose a non parametric estimator of the unknown translated density. In case the latent variables form a Markov chain (Hidden Markov models), we prove an oracle inequality leading to the fact that this estimator is minimax adaptive over regularity classes of densities.
Type de document :
Pré-publication, Document de travail
2013
Liste complète des métadonnées

Littérature citée [30 références]  Voir  Masquer  Télécharger

https://hal.archives-ouvertes.fr/hal-00786750
Contributeur : Judith Rousseau <>
Soumis le : dimanche 10 février 2013 - 15:09:11
Dernière modification le : jeudi 22 novembre 2018 - 01:20:51
Document(s) archivé(s) le : samedi 11 mai 2013 - 03:52:51

Fichiers

Nonparameldep-Adapt.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-00786750, version 1
  • ARXIV : 1302.2345

Collections

Citation

Elisabeth Gassiat, Judith Rousseau. Non parametric finite translation mixtures with dependent regime. 2013. 〈hal-00786750〉

Partager

Métriques

Consultations de la notice

438

Téléchargements de fichiers

369