Threshold Selection in Extreme Value Analysis

The main objective of statistics of extremes is the prediction of rare events, and its primary problem has been the estimation of the extreme value index (EVI). Whenever we are interested in large values, such estimation is usually performed on the basis of the largest k + 1 order statistics in the sample or on the excesses over a high level u. The question that has been often addressed in practical applications of extreme value theory is the choice of either k or u, and an adaptive EVI-estimation. Such a choice can be either heuristic or based on sample paths stability or on the minimization of a mean squared error estimate as a function of k. Some of these procedures will be reviewed. Despite of the fact that the methods provided can be applied, with adequate modifications, to any real EVI and not only to the adaptive EVI-estimation but also to the adaptive estimation of other relevant right-tail parameters, we shall illustrate the methods essentially for the EVI and for heavy tails, i.e., for a positive EVI.

[1]  Piet Groeneboom,et al.  Kernel-type estimators for the extreme value index , 2003 .

[2]  Frederico Caeiro,et al.  Semi-parametric tail inference through probability-weighted moments , 2011 .

[3]  P. Hall.  On Some Simple Estimates of an Exponent of Regular Variation , 1982 .

[4]  Sidney I. Resnick,et al.  How to make a Hill Plot , 2000 .

[5]  Frederico Caeiro,et al.  An Overview And Open Research Topics In Statistics Of Univariate Extremes , 2012 .

[6]  M. Ivette Gomes,et al.  A new class of semi-parametric estimators of the second order parameter. , 2003 .

[7]  M. Gomes,et al.  Modeling Extreme Events: Sample Fraction Adaptive Choice in Parameter Estimation , 2012 .

[8]  Alan H. Welsh,et al.  Adaptive Estimates of Parameters of Regular Variation , 1985 .

[9]  Paul Deheuvels,et al.  Kernel Estimates of the Tail Index of a Distribution , 1985 .

[10]  M. Ivette Gomes,et al.  The Bootstrap Methodology in Statistics of Extremes—Choice of the Optimal Sample Fraction , 2001 .

[11]  Jan Beirlant,et al.  Excess functions and estimation of the extreme-value index , 1996 .

[12]  Edgar Kaufmann,et al.  Selecting the optimal sample fraction in univariate extreme value estimation , 1998 .

[13]  S. Resnick.  Heavy tail modeling and teletraffic data: special invited paper , 1997 .

[14]  J. Geluk,et al.  Regular variation, extensions and Tauberian theorems , 1987 .

[15]  A Note on the Adaptive Choice of the Optimal Threshold in Extreme Value Analysis , 2011 .

[16]  M. J. Martins,et al.  “Asymptotically Unbiased” Estimators of the Tail Index Based on External Estimation of the Second Order Parameter , 2002 .

[17]  Peter Hall,et al.  Using the bootstrap to estimate mean squared error and select smoothing parameter in nonparametric problems , 1990 .

[18]  J. Hüsler,et al.  Statistical Analysis of Extreme Values with Applications to Insurance, Finance, Hydrology and Other Fields , 2007 .

[19]  M. Ivette Gomes,et al.  Extreme Value Theory and Statistics of Univariate Extremes: A Review , 2015 .

[20]  Björn Vandewalle,et al.  A heuristic adaptive choice of the threshold for bias-corrected Hill estimators , 2008 .

[21]  Zhang Chun-ying.  Threshold selection in tail index estimation , 2006 .

[22]  M. Ivette Gomes,et al.  Reduced-Bias Tail Index Estimators Under a Third-Order Framework , 2009 .

[23]  B. M. Hill,et al.  A Simple General Approach to Inference About the Tail of a Distribution , 1975 .

[24]  M. Ivette Gomes,et al.  Reduced-Bias Location-Invariant Extreme Value Index Estimation: A Simulation Study , 2011, Commun. Stat. Simul. Comput..

[25]  Jan Beirlant,et al.  Tail Index Estimation and an Exponential Regression Model , 1999 .

[26]  Fernanda Figueiredo,et al.  Adaptive estimation of heavy right tails: resampling-based methods in action , 2012 .

[27]  Stefan Wager,et al.  Subsampling extremes: From block maxima to smooth tail estimation , 2012, J. Multivar. Anal..

[28]  M. Gomes,et al.  Adaptive Reduced-Bias Tail Index and VaR Estimation via the Bootstrap Methodology , 2011 .

[29]  Hogeschool-Universiteit Brussel,et al.  GENERALIZED SUM PLOTS , 2011 .

[30]  M. Ivette Gomes,et al.  Adaptive PORT–MVRB estimation: an empirical comparison of two heuristic algorithms , 2013 .

[31]  S. Resnick,et al.  The qq-estimator and heavy tails , 1996 .

[32]  A. Frigessi,et al.  A Dynamic Mixture Model for Unsupervised Tail Estimation without Threshold Selection , 2002 .

[33]  S. Csörgo,et al.  Estimating the tail index , 1998 .

[34]  R. Reiss,et al.  Statistical Analysis of Extreme Values-with applications to insurance , 1997 .

[35]  Carl Scarrott,et al.  A Review of Extreme Value Threshold Estimation and Uncertainty Quantification , 2012 .

[36]  Eric P. Smith,et al.  An Introduction to Statistical Modeling of Extreme Values , 2002, Technometrics.

[37]  S. Resnick,et al.  Smoothing the Hill estimator , 1997 .

[38]  J. Teugels,et al.  Statistics of Extremes , 2004 .

[39]  J. Teugels,et al.  Tail Index Estimation, Pareto Quantile Plots, and Regression Diagnostics , 1996 .

[40]  Armelle Guillou,et al.  A diagnostic for selecting the threshold in extreme value analysis , 2001 .

[41]  M. Ivette Gomes,et al.  DIRECT REDUCTION OF BIAS OF THE CLASSI- CAL HILL ESTIMATOR ⁄ , 2005 .

[42]  L. Haan,et al.  Using a Bootstrap Method to Choose the Sample Fraction in Tail Index Estimation , 2000 .

[43]  M. J. Martins,et al.  Averages of Hill estimators , 2004 .

[44]  J. Teugels,et al.  Practical Analysis of Extreme Values , 1996 .

[45]  M. Gomes,et al.  A computational study of a quasi-PORT methodology for VaR based on second-order reduced-bias estimation , 2012 .

[46]  M. Ivette Gomes,et al.  A Sturdy Reduced-Bias Extreme Quantile (VaR) Estimator , 2007 .

[47]  George Michailidis,et al.  A Diagnostic Plot for Estimating the Tail Index of a Distribution , 2004 .

[48]  Jan Beirlant,et al.  On Exponential Representations of Log-Spacings of Extreme Order Statistics , 2002 .