 A Review of More than One Hundred Pareto-Tail Index EstimatorsStatistica, 2020, vol. 80, issue 3, 245-299 Abstract: Heavy-tailed distributions are often encountered in economics, finance, biology, telecommunications, geology, etc. The heaviness of a tail is measured by a tail index. Numerous methods for tail index estimation have been proposed. This paper reviews more than one hundred Pareto (and equivalent) tail index estimators. It focuses on univariate estimators for non-truncated data. We discuss the basic features of these estimators and provide their analytical expressions. As samples from heavy-tailed distributions are often analysed by researchers from various sciences, the paper provides nontechnical explanations of the methods, so as to be understood by researchers with intermediate skills in statistics. We also discuss the strengths and weaknesses of the estimators, if known. The main focus of the paper is semi-parametric estimators; however, a number of parametric estimators under-represented in previous reviews are also discussed. The paper can be viewed as a catalog or a reference work on Pareto-tail index estimators. A Monte-Carlo comparison of more than 90 estimators is presented. Keywords: Heavy tails; Pareto distribution; Tail index; Review (search for similar items in EconPapers) There are no downloads for this item, see the EconPapers FAQ for hints about obtaining it. Related works: Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text Persistent link: https://EconPapers.repec.org/RePEc:bot:rivsta:v:80:y:2020:i:3:p:245-299 Access Statistics for this article Statistica is currently edited by Department of Statistics, University of Bologna More articles in Statistica from Department of Statistics, University of Bologna Contact information at EDIRC. |
Is your work missing from RePEc? Here is how to contribute.
Questions or problems? Check the EconPapers FAQ or send mail to .
EconPapers is hosted by the
School of Business at Örebro University.