Extreme Value Inference for General Heterogeneous Data
Authors:
Preprint
- 1 January 2024
- preprint
- Published by Elsevier in SSRN Electronic Journal
Abstract
We extend extreme value statistics to the general setting of independent data with possibly very different distributions, whereby the extreme value index of the average distribution can be negative, zero, or positive. We present novel asymptotic theory for the moment estimator, based on a uniform central limit theorem for the underlying weighted tail empirical process. We find that, due to the heterogeneity of the data, the asymptotic variance of the moment estimator can be much smaller than that in the i.i.d. case. We also unravel the improved performance of high quantile and endpoint estimators in this setup. In case of a heavy tail, we ameliorate the Hill estimator by taking an optimal combination of the Hill and the moment estimator. Simulations show the good finite-sample behavior of our limit results. Finally we present applications to the maximum lifespan of monozygotic twins and to the tail heaviness of energies of earthquakes around the globe.Keywords
This publication has 14 references indexed in Scilit:
- Trends in Extreme Value IndicesJournal of the American Statistical Association, 2020
- Heavy-Tailed Time Series2020
- Limits to Human Life Span Through Extreme Value TheoryJournal of the American Statistical Association, 2019
- Statistics of Heteroscedastic ExtremesJournal of the Royal Statistical Society Series B: Statistical Methodology, 2014
- Extreme Value Theory2006
- Statistics of Extremes2004
- Weighted approximations of tail processes for $\beta$-mixing random variablesThe Annals of Applied Probability, 2000
- Weak Convergence and Empirical Processes1996
- Models for Exceedances Over High ThresholdsJournal of the Royal Statistical Society Series B: Statistical Methodology, 1990
- Functional central limit theorems for processes with positive drift and their inversesProbability Theory and Related Fields, 1972