Ítem


Lasso regression method for a compositional covariate regularised by the norm L1 pairwise logratio

Lasso regression methods include a penalty function expressed in terms of a norm defined in the space of model coefficients. The norm plays a key role as regards the way coefficients can become irrelevant in the model. For models with a compositional covariate, the norm should be coherent with the Aitchison geometry. The proposed method is based on a newly-defined compositional norm called L1 pairwise logratio. The novel approach allows one to construct an appropriate basis through a sequential binary partition for discriminating between balances that influence the response variable and those that have no effect. This generalised Lasso regression scheme is illustrated with the analysis of a geochemical data set

This research was supported by the Ministerio de Ciencia e Innovación under the project “CODA-GENERA” (Ref. PID2021-123833OB-I00) and the grant PRE2019-090976; and by the Agència de Gestió d’Ajuts Universitaris i de Recerca of the Generalitat de Catalunya under the project “COSDA” (Ref. 2021SGR01197)

Open Access funding provided thanks to the CRUE-CSIC agreement with Elsevier

Elsevier

Director: Agencia Estatal de Investigación
Autor: Saperas Riera, Jordi
Mateu i Figueras, Glòria
Martín Fernández, Josep Antoni
Data: desembre 2023
Resum: Lasso regression methods include a penalty function expressed in terms of a norm defined in the space of model coefficients. The norm plays a key role as regards the way coefficients can become irrelevant in the model. For models with a compositional covariate, the norm should be coherent with the Aitchison geometry. The proposed method is based on a newly-defined compositional norm called L1 pairwise logratio. The novel approach allows one to construct an appropriate basis through a sequential binary partition for discriminating between balances that influence the response variable and those that have no effect. This generalised Lasso regression scheme is illustrated with the analysis of a geochemical data set
This research was supported by the Ministerio de Ciencia e Innovación under the project “CODA-GENERA” (Ref. PID2021-123833OB-I00) and the grant PRE2019-090976; and by the Agència de Gestió d’Ajuts Universitaris i de Recerca of the Generalitat de Catalunya under the project “COSDA” (Ref. 2021SGR01197)
Open Access funding provided thanks to the CRUE-CSIC agreement with Elsevier
Format: application/pdf
Accés al document: http://hdl.handle.net/10256/24248
Llenguatge: eng
Editor: Elsevier
Col·lecció: info:eu-repo/semantics/altIdentifier/doi/10.1016/j.gexplo.2023.107327
info:eu-repo/semantics/altIdentifier/issn/0375-6742
info:eu-repo/semantics/altIdentifier/eissn/1879-1689
PID2021-123833OB-I00
info:eu-repo/grantAgreement/AEI/Plan Estatal de Investigación Científica y Técnica y de Innovación 2021-2023/PID2021-123833OB-I00/ES/GENERATION AND TRANSFER OF COMPOSITIONAL DATA ANALYSIS KNOWLEDGE/
Drets: Reconeixement 4.0 Internacional
URI Drets: http://creativecommons.org/licenses/by/4.0
Matèria: Anàlisi de regressió
Regression analysis
Títol: Lasso regression method for a compositional covariate regularised by the norm L1 pairwise logratio
Tipus: info:eu-repo/semantics/article
Repositori: DUGiDocs

Matèries

Autors