LORENZO, Hadrien; CLOAREC, Olivier; THIÉBAUT, Rodolphe; SARACCO, Jérôme

doi:10.1002/sam.11558

Metadatos

Mostrar el registro completo del ítem

Licencia de uso del documento

LORENZO, Hadrien
Méthodes avancées d’apprentissage statistique et de contrôle [ASTRAL]

CLOAREC, Olivier
Sartorius Stedim France S.A.S. [Aubagne]

THIÉBAUT, Rodolphe
Statistics In System biology and Translational Medicine [SISTM]
Bordeaux population health [BPH]
Vaccine Research Institute [Créteil, France] [VRI]

Idioma

Article de revue

Este ítem está publicado en

Statistical Analysis and Data Mining. 2022, vol. 15, n° 2, p. 264-282

Wiley

Resumen en inglés

In the supervised high dimensional settings with a large number of variables and a low number of individuals, variable selection allows a simpler interpretation and more reliable predictions. That subspace selection is often managed with supervised tools when the real question is motivated by variable prediction. We propose a Partial Least Square (PLS) based method, called data-driven sparse PLS (ddsPLS), allowing variable selection both in the covariate and the response parts using a single hyper-parameter per component. The subspace estimation is also performed by tuning a number of underlying parameters. The ddsPLS method is compared to existing methods such as classical PLS and two well established sparse PLS methods through numerical simulations. The observed results are promising both in terms of variable selection and prediction performance. This methodology is based on new prediction quality descriptors associated with the classical R 2 and Q 2 and uses bootstrap sampling to tune parameters and select an optimal regression model.< Leer menos

Palabras clave en inglés

PLS regression

Supervised learning

Variable selection

Soft thresholding

Multi-block data

Metadatos

Compartir este ítem

Licencia de uso del documento

Data-Driven Sparse Partial Least Squares

Idioma

Este ítem está publicado en

Resumen en inglés

Palabras clave en inglés

URI

DOI

Orígen

Centros de investigación