Empirical Likelihood Based Testing for Multivariate Regular Variation

John Einmahl, Andrea Krajina

Research output: Working paperDiscussion paperOther research output

135 Downloads (Pure)

Abstract

Multivariate regular variation is a common assumption in the statistics literature and needs to be verified in real-data applications. We develop a novel hypothesis test for multivariate regular variation, employing localized empirical likelihood. We establish the weak convergence of the test statistic to a non-standard, distribution-free limit and hence can provide universal critical values for the test. We show the very good finite-sample behavior of the procedure through simulations and apply the test to several real-data examples.
Original languageEnglish
Place of PublicationTilburg
PublisherCentER, Center for Economic Research
Number of pages19
Volume2023-001
Publication statusPublished - 9 Jan 2023

Publication series

NameCentER Discussion Paper
Volume2023-001

Keywords

  • asymptotic theory
  • distribution-free
  • empirical likelihood
  • empirical process
  • multivariate tail
  • regular variation
  • tail index

Fingerprint

Dive into the research topics of 'Empirical Likelihood Based Testing for Multivariate Regular Variation'. Together they form a unique fingerprint.

Cite this