A hybrid-Hill estimator enabled by heavy-tailed block maxima

TL;DR

This paper introduces a hybrid-Hill estimator that unifies block maxima and peaks-over-threshold methods, enabling more efficient and bias-reduced extreme value inference without large block size requirements.

Contribution

It proposes a new universality class of extreme value distributions and a hybrid estimator that improves inference by combining the strengths of existing approaches.

Findings

The hybrid-Hill estimator outperforms maximum likelihood estimation in bias reduction.

A new universality class of extreme value distributions is introduced.

Extensions to dependent and non-stationary data are mapped out.

Abstract

When analysing extreme values, two alternative statistical approaches have historically been held in contention: the block maxima method (or annual maxima method, spurred by hydrological applications) and the peaks-over-threshold. Clamoured amongst statisticians as wasteful of potentially informative data, the block maxima method gradually fell into disfavour whilst peaks-over-threshold-based methodologies climbed to the centre stage of extreme value statistics. This paper devises a hybrid method which reconciles these two hitherto disconnected approaches. Appealing in its simplicity, our main result introduces a new universality class of extreme value distributions that discards the customary requirement of a sufficiently large block size for the plausible block maxima-fit to an extreme value distribution. Natural extensions to dependent and/or non-stationary settings are mapped out. We advocate that inference should be drawn solely on larger block maxima, from which practice the mainstream peaks-over-threshold methodology coalesces: the asymptotic properties of the hybrid-Hill estimator herald more than its efficiency, but rather that a fully-fledged unified semi-parametric stream of statistics for extreme values is viable. A reduced-bias off-shoot of the hybrid-Hill estimator provably outclasses the incumbent maximum likelihood estimation that relies on a numerical fit to the entire sample of block maxima.