Copula Models of the Joint Distribution of Exchange Rates
Antonov I. N. (),
Knyazev A. G. () and
Lepekhin O. A. ()
Additional contact information
Antonov I. N.: Astrakhan State University
World of economics and management / Vestnik NSU. Series: Social and Economics Sciences, 2016, vol. 16, issue 4, 20-38
Abstract:
The paper aims at investigating the joint distribution of currency rates using HAC, HKC and Vine copulas in several time periods. Models were constructed using Archimedean copulas including Gumbel-Hougaard, Joe BB1 and Frank copulas, and their parameters were estimated by maximum likelihood. The best models were built using hierarchical Archimedean copulas and the worst were obtained with vine copulas. In comparison with the HAC, the main advantage of hierarchical Kendall copulas is the possibility to use a two-parameter copula Joe BB1. The best models were obtained with Frank copula, while Gumbel-Hougaard copula has shown a decent result only in the third period. Additionally, in this paper was made an attempt to get the forecast of exchange rates using Kendall’s and Marshall-Olkin’s algorithms. The most accurate forecast was obtained with Gumbel-Hougaard copula for euro and franc.
Keywords: Archimedean copulas; currency; forecast; Frank copula; Gumbel-Hougaard copula; HAC; HKC; Joe BB1 copula; Marshall-Olkin’s algorithm; sampling via Kendall’s Distribution; Vine. (search for similar items in EconPapers)
JEL-codes: C58 (search for similar items in EconPapers)
Date: 2016
References: View references in EconPapers View complete reference list from CitEc
Citations:
Downloads: (external link)
http://www.nsu.ru/rs/mw/link/Media:/57475/02.pdf
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:nos:wjflnh:2016_4_02e
Access Statistics for this article
More articles in World of economics and management / Vestnik NSU. Series: Social and Economics Sciences from Socionet
Bibliographic data for series maintained by Вестник НГУ социально-экономические науки ().