Linear Regression in High Dimension and/or ...
Document type :
Partie d'ouvrage: Chapitre
DOI :
Title :
Linear Regression in High Dimension and/or for Correlated Inputs
Author(s) :
Jacques, Julien [Auteur]
Entrepôts, Représentation et Ingénierie des Connaissances [ERIC]
Laboratoire Paul Painlevé - UMR 8524 [LPP]
MOdel for Data Analysis and Learning [MODAL]
Fraix-Burnet, Didier [Auteur]
Institut de Planétologie et d'Astrophysique de Grenoble [IPAG]
Entrepôts, Représentation et Ingénierie des Connaissances [ERIC]
Laboratoire Paul Painlevé - UMR 8524 [LPP]
MOdel for Data Analysis and Learning [MODAL]
Fraix-Burnet, Didier [Auteur]
Institut de Planétologie et d'Astrophysique de Grenoble [IPAG]
Scientific editor(s) :
D; Fraix-Burnet
D. Valls-Gabaud
D. Valls-Gabaud
Book title :
Statistics for Astrophysics Methods and Applications of the Regression
Publisher :
EDP Sciences
Publication date :
2014
ISBN :
978-2-7598-1729-0
HAL domain(s) :
Physique [physics]/Astrophysique [astro-ph]
Mathématiques [math]/Statistiques [math.ST]
Mathématiques [math]/Statistiques [math.ST]
English abstract : [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 ...
Show more >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.Show less >
Show more >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.Show less >
Language :
Anglais
Audience :
Internationale
Popular science :
Non
Collections :
Source :
Files
- Open access
- Access the document