Tail fitting for truncated and non-truncated Pareto-type distributions

DOI10.1007/S10687-016-0247-3MaRDI QIDQ508715zbMATH OpenOpenAlexFDO

Authors Ivette Gomes, J. Beirlant, M. Isabel Fraga Alves

Publication date 8 February 2017

Published in Extremes (Search for Journal in Brave)

Full work available at URL https://arxiv.org/abs/1505.05189

zbMATH Keywords

truncationextreme quantilesendpointPareto-type distributionsQQ-plots

Mathematics Subject Classification ID

Probability distributions: general theory (60E05) Nonparametric estimation (62G05) Nonparametric hypothesis testing (62G10) Asymptotic properties of nonparametric inference (62G20) Statistics of extreme values; tail inference (62G32)

Abstract: Recently some papers, such as Aban, Meerschaert and Panorska (2006), Nuyts (2010) and Clark (2013), have drawn attention to possible truncation in Pareto tail modelling. Sometimes natural upper bounds exist that truncate the probability tail, such as the Maximum Possible Loss in insurance treaties. At other instances ultimately at the largest data, deviations from a Pareto tail behaviour become apparent. This matter is especially important when extrapolation outside the sample is required. Given that in practice one does not always know whether the distribution is truncated or not, we consider estimators for extreme quantiles both under truncated and non-truncated Pareto-type distributions. Hereby we make use of the estimator of the tail index for the truncated Pareto distribution first proposed in Aban {it et al.} (2006). We also propose a truncated Pareto QQ-plot and a formal test for truncation in order to help deciding between a truncated and a non-truncated case. In this way we enlarge the possibilities of extreme value modelling using Pareto tails, offering an alternative scenario by adding a truncation point $T$ that is large with respect to the available data. In the mathematical modelling we hence let $Toinfty$ at different speeds compared to the limiting fraction ($k/no0$) of data used in the extreme value estimation. This work is motivated using practical examples from different fields of applications, simulation results, and some asymptotic results.

Recommendations

• scientific article; zbMATH DE number 5791351
• Parameter Estimation for the Truncated Pareto Distribution
• A nonparametric estimator for the conditional tail index of Pareto-type distributions
• Extended generalised Pareto models for tail estimation
• scientific article; zbMATH DE number 3919550
• Estimating the parameters of a tapered Pareto distribution
• Estimating a tail exponent by modelling departure from a Pareto distribution
• A robust estimator for the tail index of Pareto-type distributions
• Pareto tail index estimation revisited

Cites work

• A moment estimator for the index of an extreme-value distribution
• A simple general approach to inference about the tail of a distribution
• A simple generalisation of the Hill estimator
• Adaptive estimation of heavy right tails: resampling-based methods in action
• Estimation of Parameters and Larger Quantiles Based on the k Largest Observations
• Extreme value theory. An introduction.
• Generalized least-squares estimators for the thickness of heavy tails
• Inference about the tail of a distribution: improvement on the Hill estimator
• On the estimation of the extreme-value index and large quantile estimation
• Parameter Estimation for the Truncated Pareto Distribution
• Regularly varying functions
• Second-order refined peaks-over-threshold modelling for heavy-tailed distributions
• Statistics of Extremes
• Tail Index Estimation, Pareto Quantile Plots, and Regression Diagnostics
• Understanding heavy tails in a bounded world or, is a truncated heavy tail heavy or not?

Cited in

(16)

• Estimating the second-order parameter of regular variation and bias reduction in tail index estimation under random truncation
• Extreme value analysis without the largest values: what can be done?
• Using jackknife to correct bias of MLE for the truncated Pareto distribution
• Robust quantile estimation under bivariate extreme value models
• Modelling censored losses using splicing: a global fit strategy with mixed Erlang and extreme value distributions
• Parameter Estimation for the Truncated Pareto Distribution
• Introduction to extreme value theory: applications to risk analysis and management
• Data-adaptive trimming of the Hill estimator and detection of outliers in the extremes of heavy-tailed data
• The PORTSEA (Portuguese School of Extremes and Applications) and a few personal scientific achievements
• Handling missing extremes in tail estimation
• A discrete truncated Zipf distribution
• TEMPERED PARETO-TYPE MODELLING USING WEIBULL DISTRIBUTIONS
• scientific article; zbMATH DE number 5791351 (Why is no real title available?)
• Comparing extreme models when the sign of the extreme value index is known
• A cluster truncated Pareto distribution and its applications
• Fitting tails affected by truncation

This page was built for publication: Tail fitting for truncated and non-truncated Pareto-type distributions

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q508715)