Title
A new method for the construction of bivariate Archimedean copulas based on the <tex>$\lambda$</tex> function A new method for the construction of bivariate Archimedean copulas based on the <tex>$\lambda$</tex> function
Author
Faculty/Department
Faculty of Applied Economics
Publication type
article
Publication
New York, N.Y. ,
Subject
Economics
Mathematics
Source (journal)
Communications in statistics : theory and methods. - New York, N.Y.
Volume/pages
40(2011) :15 , p. 2670-2679
ISSN
0361-0926
ISI
000290406700004
Carrier
E
Target language
English (eng)
Full text (Publishers DOI)
Affiliation
University of Antwerp
Abstract
We introduce and discuss a general method for constructing bivariate Archimedean copula families. The central item in our method is the function [image omitted] (t ∈ [0, 1]), where &#981; is the generator of the Archimedean copula. The construction of new copulas by means of λ has several advantages. The most important one is the straightforward relationship between the λ function and Kendall's τ and the coefficients of upper and lower tail dependence λL and λU, as defined in Joe (1997), which makes it possible to use these quantities as copula parameters and to control them independently of each other. Furthermore, the λ-method allows to construct multi-parameter families in a clear and organized way. The methodology is explained and illustrated by two- and three-parameter copula families.
E-info
http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000290406700004&DestLinkType=RelatedRecords&DestApp=ALL_WOS&UsrCustomerID=ef845e08c439e550330acc77c7d2d848
http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000290406700004&DestLinkType=FullRecord&DestApp=ALL_WOS&UsrCustomerID=ef845e08c439e550330acc77c7d2d848
http://gateway.webofknowledge.com/gateway/Gateway.cgi?GWVersion=2&SrcApp=PARTNER_APP&SrcAuth=LinksAMR&KeyUT=WOS:000290406700004&DestLinkType=CitingArticles&DestApp=ALL_WOS&UsrCustomerID=ef845e08c439e550330acc77c7d2d848
Handle