Gradient boosting for extreme quantile regression

Gradient boosting for extreme quantile regression

Velthoen, J.J. (TU Delft Statistics)
Dombry, Clément (Université de Bourgogne)
Cai, Juan Juan (Vrije Universiteit Amsterdam)
Engelke, Sebastian (Université de Genève)

2023

Extreme quantile regression provides estimates of conditional quantiles outside the range of the data. Classical quantile regression performs poorly in such cases since data in the tail region are too scarce. Extreme value theory is used for extrapolation beyond the range of observed values and estimation of conditional extreme quantiles. Based on the peaks-over-threshold approach, the conditional distribution above a high threshold is approximated by a generalized Pareto distribution with covariate dependent parameters. We propose a gradient boosting procedure to estimate a conditional generalized Pareto distribution by minimizing its deviance. Cross-validation is used for the choice of tuning parameters such as the number of trees and the tree depths. We discuss diagnostic plots such as variable importance and partial dependence plots, which help to interpret the fitted models. In simulation studies we show that our gradient boosting procedure outperforms classical methods from quantile regression and extreme value theory, especially for high-dimensional predictor spaces and complex parameter response surfaces. An application to statistical post-processing of weather forecasts with precipitation data in the Netherlands is proposed.

60G70
62G08
Extreme quantile regression
Extreme value theory
Generalized Pareto distribution
Gradient boosting
Tree-based methods

http://resolver.tudelft.nl/uuid:5834a75d-b3ab-4120-8153-b31188b7fd34

https://doi.org/10.1007/s10687-023-00473-x

1386-1999

Extremes: statistical theory and applications in science, engineering and economics, 26 (4), 639-667

Institutional Repository

journal article

© 2023 J.J. Velthoen, Clément Dombry, Juan Juan Cai, Sebastian Engelke