Variable selection and forecasting via automated methods for linear models: LASSO/adaLASSO and Autometrics - HAL-SHS - Sciences de l'Homme et de la Société Accéder directement au contenu
Autre Publication Scientifique Année : 2017

Variable selection and forecasting via automated methods for linear models: LASSO/adaLASSO and Autometrics

Résumé

In this paper we compare two approaches of model selection methods for linear regression models: classical approach - Autometrics (automatic general-to-specific selection) — and statistical learning - LASSO (ℓ1-norm regularization) and adaLASSO (adaptive LASSO). In a simulation experiment, considering a simple setup with orthogonal candidate variables and independent data, we compare the performance of the methods concerning predictive power (out-of-sample forecast), selection of the correct model (variable selection) and parameter estimation. The case where the number of candidate variables exceeds the number of observation is considered as well. Finally, in an application using genomic data from a highthroughput experiment we compare the predictive power of the methods to predict epidermal thickness in psoriatic patients.
Fichier principal
Vignette du fichier
13080R.pdf (1.91 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

halshs-00917797 , version 1 (12-12-2013)
halshs-00917797 , version 2 (29-12-2017)

Identifiants

  • HAL Id : halshs-00917797 , version 2

Citer

Camila Epprecht, Dominique Guegan, Álvaro Veiga, Joel Correa da Rosa. Variable selection and forecasting via automated methods for linear models: LASSO/adaLASSO and Autometrics. 2017. ⟨halshs-00917797v2⟩
545 Consultations
2249 Téléchargements

Partager

Gmail Facebook X LinkedIn More