The revisited knockoffs method for variable selection in $L_1$-penalised regressions - Archive ouverte HAL Accéder directement au contenu
Pré-Publication, Document De Travail Année : 2019

The revisited knockoffs method for variable selection in $L_1$-penalised regressions

Résumé

We consider the problem of variable selection in regression models. In particular, we are interested in selecting explanatory covariates linked with the response variable and we want to determine which covariates are relevant, that is which covariates are involved in the model. In this framework, we deal with $L_1$-penalised regression models. To handle the choice of the penalty parameter to perform variable selection, we develop a new method based on the knockoffs idea. This revisited knockoffs method is general, suitable for a wide range of regressions with various types of response variables. Besides, it also works when the number of observations is smaller than the number of covariates and gives an order of importance of the covariates. Finally, we provide many experimental results to corroborate our method and compare it with other variable selection methods.
Fichier principal
Vignette du fichier
Rev KO - Hal ArXiv.pdf (520.49 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01799914 , version 1 (25-05-2018)
hal-01799914 , version 2 (17-11-2019)

Identifiants

  • HAL Id : hal-01799914 , version 2

Citer

Anne Gégout-Petit, Aurélie Muller-Gueudin, Clémence Karmann. The revisited knockoffs method for variable selection in $L_1$-penalised regressions. 2019. ⟨hal-01799914v2⟩
299 Consultations
409 Téléchargements

Partager

Gmail Facebook X LinkedIn More