Regression function estimation on non compact support as a partly inverse problem - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2018

Regression function estimation on non compact support as a partly inverse problem

Résumé

This paper is about nonparametric regression function estimation, first in the independent setting and in a second stage, in the context of an autoregressive model or of discrete time observation of a diffusion process, both settings corresponding to dependent variables. Our estimator is a one step projection estimator obtained by least-squares contrast minimization. The specificity of our work is to consider a new model selection procedure including a cutoff for the underlying matrix inversion, and to provide theoretical risk bounds that apply to non compactly supported bases, a case which was specifically excluded of all previous results. Upper and lower bounds for new rates are provided.
Fichier principal
Vignette du fichier
NonCompactRegV3.pdf (990.05 Ko) Télécharger le fichier
Origine Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01690856 , version 1 (23-01-2018)
hal-01690856 , version 2 (05-04-2018)
hal-01690856 , version 3 (11-07-2018)
hal-01690856 , version 4 (18-10-2018)

Identifiants

  • HAL Id : hal-01690856 , version 3

Citer

Fabienne Comte, V Genon-Catalot. Regression function estimation on non compact support as a partly inverse problem. 2018. ⟨hal-01690856v3⟩
352 Consultations
508 Téléchargements

Partager

Gmail Mastodon Facebook X LinkedIn More