A New Regression-Based Tail Index Estimator

Jo�ão Nicolau; Paulo M.M. Rodrigues

doi:10.1162/rest_a_00768

← Search

A New Regression-Based Tail Index Estimator

Jo�ão Nicolau¹; Paulo M.M. Rodrigues²

¹ ISEG-Universidade de Lisboa and REM/CEMAPRE · ² Banco de Portugal and NovaSBE, Universidade Nova de Lisboa

The Review of Economics and Statistics 2019 open access

A new regression-based approach for the estimation of the tail index of heavy-tailed distributions with several important properties is introduced. First, it provides a bias reduction when compared to available regression-based methods; second, it is resilient to the choice of the tail length used for the estimation of the tail index; third, when the effect of the slowly varying function at infinity of the Pareto distribution vanishes slowly, it continues to perform satisfactorily; and fourth, it performs well under dependence of unknown form. An approach to compute the asymptotic variance under time dependence and conditional heteroskcedasticity is also provided.

DOI: 10.1162/rest_a_00768
Volume: 101 (4)
Pages: 667-680
Language: en
Export: BibTeX
Sources: openalex crossref