Zeitschrift für Energiewirtschaft

, Volume 37, Issue 2, pp 107–126 | Cite as

A Multivariate Commodity Analysis with Time-Dependent Volatility—Evidence from the German Energy Market

  • Rüdiger KieselEmail author
  • Kevin Metka


In recent years commodity markets (in particular electricity, coal, and emissions) encountered extreme price movements and phases of high price volatility. Utility companies are naturally exposed to these kinds of market movements and thus have to set-up an appropriate risk management system. We show that the nonstationary behavior of recent energy prices can be captured by time-dependent (and possibly stochastic) volatility models. We compare their statistical performance and their impact on risk management applications by calculating risk metrics such as value-at-risk. Based on a comprehensive backtesting study we conclude that our suggested models outperform stationary models in most cases and therefore should be considered superior for risk management applications.


German electricity market Cross-commodity Time-dependent volatility Risk management Backtesting Value-at-risk 

Eine multivariate Commodity Analyse mit zeitabhängiger Volatilität – Am Beispiel des deutschen Energiemarktes


In den letzten Jahren waren die Rohstoffmärkte, insbesondere für Elektrizität, Kohle und Emmissionszertifikate, von großen Preisausschlägen und Phasen hoher Volatilität gekennzeichnet. Energieversorgungsunternehmen sind gegenüber solchen Preisschwankungen exponiert und müssen adäquate Risikomanagementsysteme einsetzen. Wir zeigen, dass das nicht-stationäre Verhalten der Preisprozesse durch zeitabhängige (und stochastische) Volatilitätsmodelle abgebildet werden kann. Wir berechnen Risikokennzahlen wie Value-at-Risk, um die statistische Modellierungsgüte und die Wirkung von Risikomanagementsystemen zu vergleichen. Im Rahmen einer umfangreichen Backtesting Studie zeigen wir, dass zeitabhängige Volatilitätsmodelle stationäre Modelle dominieren und damit für Risikomanagement Zwecke vorzuziehen sind.


  1. Morgan JP/Reuters (1996) RiskMetrics. Technical document Google Scholar
  2. Barndorff-Nielsen OE (1978) Hyperbolic distributions and distributions on hyperbolae. Scand J Stat Google Scholar
  3. Benth FE (2011) The stochastic volatility model of Barndorff-Nielsen and Shephard in commodity markets. Math Finance 21(4):595–625 MathSciNetzbMATHGoogle Scholar
  4. Benth FE, Benth J (2004) The normal inverse Gaussian distribution and spot price modelling in energy markets. Int J Theor Appl Finance 7(2):177–192 zbMATHCrossRefGoogle Scholar
  5. Bollerslev T (1986) Generalized autoregressive conditional heteroscedasticity. J Econom 31:307–327 MathSciNetzbMATHCrossRefGoogle Scholar
  6. Bollerslev T, Litvinova J, Tauchen G (2006) Leverage and volatility feedback effects in high-frequency data. J Financ Econom 4:353–384 CrossRefGoogle Scholar
  7. Börger R, Cartea A, Kiesel R, Schindlmayr G (2009) Cross-commodity analysis and applications to risk management. J Futures Mark 29(3) Google Scholar
  8. Brock W, Hsieh D, LeBaron B (1991) Nonlinear dynamics, chaos, and instability: statistical theory and economic evidence. MIT Press, Cambridge Google Scholar
  9. Brock WA, Dechert WD, Scheinkman JA, LeBaron B (1987) A test for independence based on the correlation dimension. Working paper Google Scholar
  10. Campbell SD (2005) A review of backtesting and backtesting procedures. Technical report, Board of Governors of the Federal Reserve System Google Scholar
  11. Carpantier J-F (2010) Commodities inventory effect. Core discussion paper Google Scholar
  12. Christoffersen PF (1998) Evaluating interval forecasts. Int Econ Rev 39(4):841–862 MathSciNetCrossRefGoogle Scholar
  13. Eberlein E, Kallsen J, Kristen J (2003) Risk management based on stochastic volatility Google Scholar
  14. Engle R (1982) Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflations. Econometrica 50:987–1008 MathSciNetzbMATHCrossRefGoogle Scholar
  15. Engle R (1990) Stock volatility and the crash of 87: discussion. Rev Financ Stud 3(1):103–106 MathSciNetCrossRefGoogle Scholar
  16. Glosten LR, Jagannathan R, Runkle DE (1993) On the relation between the expected value of the volatility of the nominal excess return on stocks. J Finance 48:1779–1801 CrossRefGoogle Scholar
  17. Hamilton JD (2009) Causes and consequences of the oil shock of 2007–2008. Working paper 15002.
  18. Härdle WK, Okhrin O (2009) De copulis non est disputandum. AStA Adv Stat Anal 94(1):1–31 CrossRefGoogle Scholar
  19. Huisman R (2009) An introduction to models for the energy markets. Riskbooks, London Google Scholar
  20. Irwin SH, Sanders DR (2010) The impact of index and swap funds on commodity futures markets: preliminary results. OECD food, griculture and fisheries working papers, No 27, OECD Publishing. doi: 10.1787/5kmd40wl1t5f-en
  21. Joe H, Xu JJ (1996) The estimation method of inference functions for margins for multivariate models. Technical report 166, Department of Statistics, University of British, Columbia Google Scholar
  22. Kiesel R, Schmidt R (2005) A survey of dependency modelling: copulas, tail dependence and estimation. In: Perraudin W (ed) Structured credit products. RISK Books, London Google Scholar
  23. Kupiec P (1995) Techniques for verifying the accuracy of risk measurement models. J Deriv 3:73–84 CrossRefGoogle Scholar
  24. Metka K (2011) Energy markets—risk management, optimal Liquidation, and derivatives. PhD thesis, University of Ulm Google Scholar
  25. Weron R (2006) Modelling and forecasting of electricity loads and prices. Wiley, New York Google Scholar

Copyright information

© Springer Fachmedien Wiesbaden 2013

Authors and Affiliations

  1. 1.Institute of Energy Trading and Financial ServicesUniversity of Duisburg-EssenEssenGermany

Personalised recommendations