Modelling dependence of extreme events in energy markets using tail copulas
http://www.erasmusenergy.com/articles/195/1/Modelling-dependence-of-extreme-events-in-energy-markets-using-tail-copulas/Page1.html
Sergej Obžigailov
MSc in Econometrics, University of Amsterdam By Sergej Obžigailov
Published on 12/13/2011
Co-Author 1: Stefan Jäschke (RWE Supply & Trading GmbH)
Co-Author 2: Karl Friedrich Siburg (Fakultät für Mathematik TU Dortmund)
Co-Author 3: Pavel A. Stoimenov (Fakultät Statistik TU Dortmund)
Abstract
This paper studies the dependence of extreme events in energy markets. Based on a large data set comprising quotes of crude oil and natural gas futures, large co-movements of commodity returns are estimated and modeled. To detect the presence of tail dependence a new method based on the concept of tail copulas which accounts for different scenarios of joint extreme outcomes is applied. Moreover, it is shown that the common practice to fit copulas to the data cannot capture the dynamics in the tail of the joint distribution and, therefore, is unsuitable for risk management purposes.
Co-Author 2: Karl Friedrich Siburg (Fakultät für Mathematik TU Dortmund)
Co-Author 3: Pavel A. Stoimenov (Fakultät Statistik TU Dortmund)
Abstract
This paper studies the dependence of extreme events in energy markets. Based on a large data set comprising quotes of crude oil and natural gas futures, large co-movements of commodity returns are estimated and modeled. To detect the presence of tail dependence a new method based on the concept of tail copulas which accounts for different scenarios of joint extreme outcomes is applied. Moreover, it is shown that the common practice to fit copulas to the data cannot capture the dynamics in the tail of the joint distribution and, therefore, is unsuitable for risk management purposes.
Modelling dependence of extreme events in energy markets using tail copulas
Co-Author 1: Stefan Jäschke (RWE Supply & Trading GmbH)
Co-Author 2: Karl Friedrich Siburg (Fakultät für Mathematik TU Dortmund)
Co-Author 3: Pavel A. Stoimenov (Fakultät Statistik TU Dortmund)
Abstract
This paper studies the dependence of extreme events in energy markets. Based on a large data set comprising quotes of crude oil and natural gas futures, large co-movements of commodity returns are estimated and modeled. To detect the presence of tail dependence a new method based on the concept of tail copulas which accounts for different scenarios of joint extreme outcomes is applied. Moreover, it is shown that the common practice to fit copulas to the data cannot capture the dynamics in the tail of the joint distribution and, therefore, is unsuitable for risk management purposes.
Key words
Extreme events, Crude oil, Natural gas, Tail dependence, Tail copulas
Co-Author 2: Karl Friedrich Siburg (Fakultät für Mathematik TU Dortmund)
Co-Author 3: Pavel A. Stoimenov (Fakultät Statistik TU Dortmund)
Abstract
This paper studies the dependence of extreme events in energy markets. Based on a large data set comprising quotes of crude oil and natural gas futures, large co-movements of commodity returns are estimated and modeled. To detect the presence of tail dependence a new method based on the concept of tail copulas which accounts for different scenarios of joint extreme outcomes is applied. Moreover, it is shown that the common practice to fit copulas to the data cannot capture the dynamics in the tail of the joint distribution and, therefore, is unsuitable for risk management purposes.
Key words
Extreme events, Crude oil, Natural gas, Tail dependence, Tail copulas