Bias correction in conditional multivariate extremes - Archive ouverte HAL Access content directly
Journal Articles Electronic Journal of Statistics Year : 2020

Bias correction in conditional multivariate extremes

Abstract

We consider bias-corrected estimation of the stable tail dependence function in the regression context. To this aim, we first estimate the bias of a smoothed estimator of the stable tail dependence function, and then we subtract it from the estimator. The weak convergence, as a stochastic process, of the resulting asymptotically unbiased estimator of the conditional stable tail dependence function, correctly normalized, is established under mild assumptions, the covariate argument being fixed. The finite sample behaviour of our asymptotically unbiased estimator is then illustrated on a simulation study and compared to two alternatives, which are not bias corrected. Finally, our methodology is applied to a dataset of air pollution measurements.
Fichier principal
Vignette du fichier
L-unbiased.pdf (413.26 Ko) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01887925 , version 1 (04-10-2018)

Identifiers

Cite

Mikael Escobar-Bach, Yuri Goegebeur, Armelle Guillou. Bias correction in conditional multivariate extremes. Electronic Journal of Statistics , 2020, 14, pp.1773-1795. ⟨10.1214/20-EJS1706⟩. ⟨hal-01887925⟩
121 View
120 Download

Altmetric

Share

Gmail Facebook X LinkedIn More