Linear Regression in High Dimension and\/or for Correlated Inputs

Jacques, Julien; Fraix-Burnet, Didier

Type de document :

Partie d'ouvrage

DOI :

10.1051/eas/1466011

URL permanente :

http://hdl.handle.net/20.500.12210/29182

Titre :

Linear Regression in High Dimension and\/or for Correlated Inputs

Auteur(s) :

Jacques, Julien [Auteur]
Fraix-Burnet, Didier [Auteur]

Éditeur(s) ou directeur(s) scientifique(s) :

D; Fraix-Burnet
D. Valls-Gabaud

Titre de l’ouvrage :

Statistics for Astrophysics Methods and Applications of the Regression

Numéro :

Pagination :

149-165

Éditeur :

EDP Sciences

Date de publication :

2014

ISBN :

978-2-7598-1729-0

Discipline(s) HAL :

Physique [physics]/Astrophysique [astro-ph]

Résumé en anglais : [en]

Ordinary least square is the common way to estimate linear regression models. When inputs are correlated or when they are too numerous, regression methods using derived inputs directions or shrinkage methods can be efficient ...
Lire la suite >Ordinary least square is the common way to estimate linear regression models. When inputs are correlated or when they are too numerous, regression methods using derived inputs directions or shrinkage methods can be efficient alternatives. Methods using derived inputs directions build new uncorrelated variables as linear combination of the initial inputs, whereas shrinkage methods introduce regularization and variable selection by penalizing the usual least square criterion. Both kinds of methods are presented and illustrated thanks to the R software on an astronomical dataset.Lire moins >

Langue :

Anglais

Audience :

Internationale

Vulgarisation :

Non

Collections :

METRICS : Evaluation des technologies de santé et des pratiques médicales - ULR 2694

Date de dépôt :

2020-06-08T14:10:19Z

Linear Regression in High Dimension and\/or ... BibTeX CSV Excel RIS

Linear Regression in High Dimension and\/or ...

BibTeX

CSV

Excel

RIS