Choosing the order of a non parametric estimator by LASSO regression - Ensai, Ecole Nationale de la Statistique et de l'Analyse de l'Information Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2018

Choosing the order of a non parametric estimator by LASSO regression

Résumé

The use of LASSO technics permit to select automatically regressors in linear or generalized linear models. We combine here this method to get a selection operator of the number of components for non parametric estimators. The method is compared to different data driven technics. Elastic Net method is also studied. Simulation show the potential of this approach. A real data in actuarial science is studied.
Fichier principal
Vignette du fichier
TestLASSO.pdf (179.79 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

hal-04463927 , version 1 (17-02-2024)

Identifiants

  • HAL Id : hal-04463927 , version 1

Citer

Yves Ngounou, Denys Pommeret. Choosing the order of a non parametric estimator by LASSO regression. 2024. ⟨hal-04463927⟩
13 Consultations
5 Téléchargements

Partager

Gmail Facebook X LinkedIn More