Discussion on "Asymptotic Analysis of Multivariate Tail Conditional Expectations," by Li Zhu and Haijun Li, Volume 16(3)

In their article the authors derive some new asymptotic relations between the multivariate tail conditional expectation and Value-at-Risk for heavy-tailed scale mixtures of multivariate distributions. This complements earlier work of Li and Sun (2009), whose results require the evaluation of univari...

Full description

Saved in:
Bibliographic Details
Published in:North American actuarial journal 2013-01, Vol.17 (1), p.98-100
Main Authors: Vanduffel, S., Yao, Jing
Format: Article
Language:English
Subjects:
Expectations
Integrals
Regression analysis
Risk management
Citations: Items that this one cites
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In their article the authors derive some new asymptotic relations between the multivariate tail conditional expectation and Value-at-Risk for heavy-tailed scale mixtures of multivariate distributions. This complements earlier work of Li and Sun (2009), whose results require the evaluation of univariate integrals of tail dependence functions, which are not always known. See also Asimit et al. (2011) for related results. The authors also show the appropriateness of their asymptotic results by comparing these with known explicit results for the multivariate elliptical case. In this discussion the they provide comment on Sections 2 and 3. In particular, they show how a proof for a key result can be simplified by conditioning first. Unless otherwise mentioned, they assume the notations and conventions from the article. All expectations and statistical quantities mentioned are tacitly assumed to exist.
ISSN:1092-0277
2325-0453
DOI:10.1080/10920277.2013.781409