On the estimation of the heavy-tail exponent in time series using the max-spectrum

DOI10.1002/ASMB.764zbMATH Open1226.91090arXiv1005.4329OpenAlexW2952588560MaRDI QIDQ3103151FDOQ3103151

George Michailidis, Stilian Stoev

Publication date: 26 November 2011

Published in: Applied Stochastic Models in Business and Industry (Search for Journal in Brave)

Abstract: This paper addresses the problem of estimating the tail index of distributions with heavy, Pareto-type tails for dependent data, that is of interest in the areas of finance, insurance, environmental monitoring and teletraffic analysis. A novel approach based on the max self-similarity scaling behavior of block maxima is introduced. The method exploits the increasing lack of dependence of maxima over large size blocks, which proves useful for time series data. We establish the consistency and asymptotic normality of the proposed max-spectrum estimator for a large class of m-dependent time series, in the regime of intermediate block-maxima. In the regime of large block-maxima, we demonstrate the distributional consistency of the estimator for a broad range of time series models including linear processes. The max-spectrum estimator is a robust and computationally efficient tool, which provides a novel time-scale perspective to the estimation of the tail--exponents. Its performance is illustrated over synthetic and real data sets.

Full work available at URL: https://arxiv.org/abs/1005.4329

Recommendations

• Cluster based inference for extremes of time series
• Moment-based tail index estimation
• Inference on the tail process with application to financial time series modeling
• Tail exponent estimation via broadband log density-quantile regression
• Estimating the heavy tail index from scaling properties

zbMATH Keywords

heavy-tailed time seriesmoving maximablock-maximaFréchet distributionheavy-tail exponentmax-spectrumMax-stable

Mathematics Subject Classification ID

Economic time series analysis (91B84) Statistical methods; risk measures (91G70)

Cites Work

• Title not available (Why is that?)
• A simple general approach to inference about the tail of a distribution
• Heavy tail modeling and teletraffic data. (With discussions and rejoinder)
• How to make a Hill plot.
• Title not available (Why is that?)
• Stochastic-Process Limits
• Limit theory for moving averages of random variables with regularly varying tail probabilities
• The supremum of a negative drift random walk with dependent heavy-tailed steps.
• Estimating a tail exponent by modelling departure from a Pareto distribution
• Title not available (Why is that?)
• Smoothing the Hill Estimator
• Confidence intervals for the tail index
• Relaxing the uniformity and independence assumptions using the concept of fractal dimension
• The Pareto-Levy Law and the Distribution of Income
• The qq-estimator and heavy tails
• Consistency of Hill's estimator for dependent data
• Estimating Heavy-Tail Exponents Through Max Self–Similarity
• Estimating the heavy tail index from scaling properties

Cited In (5)

• Construction of the tetration distribution based on the continuous iteration of the exponential-minus-one function
• LADE-based inferences for autoregressive models with heavy-tailed G-GARCH(1, 1) noise
• Local-maximum-based tail index estimator
• Title not available (Why is that?)
• Self-weighted LAD-based inference for heavy-tailed threshold autoregressive models

This page was built for publication: On the estimation of the heavy-tail exponent in time series using the max-spectrum

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3103151)