Extreme partial least-squares regression - Archive ouverte HAL Access content directly
Conference Papers Year : 2021

Extreme partial least-squares regression

Abstract

In this communication, we propose a new approach, called Extreme-PLS, for dimension reduction in regression and adapted to distribution tails. The goal is to find linear combinations of predictors that best explain the extreme values of the response variable by maximizing the associated covariance. This adaptation of the PLS estimator to the extreme-value framework is achieved in the context of a non-linear inverse regression model. In practice, it allows to quantify the effect of the covariates on the extreme values of the response variable in a simple and interpretable way. Moreover, it should yield improved results for most estimators dealing with conditional extreme values thanks to the dimension reduction achieved in the projection step. From the theoretical point of view, the asymptotic normality of the Extreme-PLS estimator is established under a heavy tail assumption but without recourse to linearity nor independence assumptions. The performance of the method is assessed on simulated data. Finally, the Extreme-PLS approach is used to analyse the influence of various parameters on extreme cereal yields collected on French farms
No file

Dates and versions

hal-03301445 , version 1 (27-07-2021)

Identifiers

  • HAL Id : hal-03301445 , version 1

Cite

Meryem Bousebata, Geoffroy Enjolras, Stéphane Girard. Extreme partial least-squares regression. EVA 2021 - 12th International Conference on Extreme Value Analysis, Jun 2021, Edinburgh / Virtual, United Kingdom. ⟨hal-03301445⟩
39 View
0 Download

Share

Gmail Facebook X LinkedIn More