A Practical Guide to Heavy Tails: Statistical Techniques and Applications / Edition 1

by Robert Adler, Raya Feldman, Murad Taqqu

Overview

Presents techniques and approaches for the statistical analysis of heavy-tailed distributions and processes, with a focus on applicability rather than theory. Emphasis is placed upon numerical problems associated with stable distributions, time series analysis and regression.

Product Details

ISBN-13:	9780817639518
Publisher:	Birkhäuser Boston
Publication date:	10/26/1998
Edition description:	1998
Pages:	534
Product dimensions:	7.01(w) x 10.00(h) x 0.05(d)

Table of Contents

Preface

Contributors

I: Applications

Heavy-Tailed Probability Distributions in the World Wide Web

Mark E. Crovella, Murad S. Taqqu, Azer Bestavros

Self-Similarity and Heavy Tails: Structural Modeling of Network Traffic

Walter Willinger, Vern Paxson, Murad S. Taqqu

Heavy Tails in High-Frequency Financial Data

Ulrich A. Muller, Michel M. Dacorogna, Olivier V. Pictet

Stable Paretian Modeling in Finance: Some Empirical and Theoretical Aspects

Stefan Mittnik, Svetlozar T. Rachev, Marc S. Paolella

Risk Management and Quantile Estimation

Franco Bassi, Paul Embrechts, Maria Kafetzaki

II: Time Series

Analysing Stable Time Series

Robert J. Adler, Raisa E. Feldman, Colin Gallagher

Inference for Linear Processes with Stable Noise

M. Calder, R. A. Davis

On Estimating the Intensity of Long-Range Dependence in Finite and Infinite Variance Time Series

Murad S. Taqqu, Vadim Teverovsky

Why Non-Linearities Can Ruin the Heavy-Tailed Modeler's Day

Sidney I. Resnick

Periodogram Estimates from Heavy-Tailed Data

T. Mikosch

Bayesian Inference for Time Series with Infinite Variance Stable Innovations

Nalini Ravishanker, Zuqiang Qiou

III: Heavy-Tail Estimation

Hill, Bootstrap and Jackknife Estimators for Heavy Tails

Olivier V. Pictet, Michel M. Dacorogna, Ulrich A. Muller

Characteristic Function Based Estimation of Stable Distribution Parameters

Stephen M. Kogon, Douglas B. Williams

IV: Regression

Bootstrapping Signs and Permutations for Regression with Heavy-Tailed Errors: a Robust Resampling

Raoul LePage, Krzysztof Podgorski, Michal Ryznar (et al.)

Linear Regression with Stable Disturbances

J. Huston McCulloch

V: Signal Processing

Deviation from Normality in Statistical Signal Processing: Parameter Estimation with Alpha-Stable Distributions

Panagiotis Tsakalides, Chrysostomos L. Nikias

Statistical Modeling and Receiver Design for Multi-User Communication Networks

George A. Tsihrintzis

VI: Model Structures

Subexponential Distributions

Charles M. Goldie, Claudia Kluppelberg

Structure of Stationary Stable Processes

Jan Rosinski

Tail Behavior of Some Shot Noise Processes

Gennady Samorodnitsky

VII: Numerical Procedures

Numerical Approximation of the Symmetric Stable Distribution and Density

J. Huston McCulloch

Table of the Maximally-Skewed Stable Distributions

J. Huston McCulloch, Don B. Panton

Multivariate Stable Distributions: Approximation, Estimation, Simulation and Identification

John P. Nolan

Univariate Stable Distributions: Parameterizations and Software

John P. Nolan

Editorial Reviews

"The editors and contributors have done a marvelous job… Professional statisticians and applied mathematicians will find it fascinating for its presentation and documentation of versatile methods for handling troublesome data." —Computing Reviews

From the Publisher

Twenty-four contributions, intended for a wide audience from various disciplines, cover a variety of applications of heavy-tailed modeling involving telecommunications, the Web, insurance, and finance. Along with discussion of specific applications are several papers devoted to time series analysis, regression, classical signal/noise detection problems, and the general structure of stable processes, viewed from a modeling standpoint. Emphasis is placed on developments in handling the numerical problems associated with stable distribution (a main technical difficulty until recently). No index. Annotation c. by Book News, Inc., Portland, Or.

Booknews