Estimating the Tail Index by using Model Averaging

TL;DR

This paper introduces a model averaging approach to estimate the tail index in peak-over-threshold problems by combining estimates across multiple thresholds using information criterion-based weights.

Contribution

It proposes a novel method that uses model averaging over a range of thresholds to improve tail index estimation accuracy.

Findings

Weighted estimates improve tail index accuracy

Model averaging reduces threshold selection bias

Method performs well across different datasets

Abstract

The ideas of model averaging are used to find weights in peak-over-threshold problems using a possible range of thresholds. A range of the largest observations are chosen and considered as possible thresholds, each time performing estimation. Weights based on an information criterion for each threshold are calculated. A weighted estimate of the threshold and shape parameter can be calculated.