Journal of Energy Markets

Risk.net

Estimation of risk measures on electricity markets with fat-tailed distributions

Emmanuel Senyo Fianu and Luigi Grossi

  • This paper explores the usefulness of EVT in VaR and ES estimation in the electricity market.
  • The model has the potential to provide more accurate quantile estimates for the electricity VaR and ES.
  • Risk measures are estimated via EVT for both lower and upper tails of the distribution of returns.

 ABSTRACT

This paper proposes an autoregressive-generalized autoregressive conditional heteroscedasticity (AR-GARCH)-type extreme value theory (EVT) model with various innovations based on value-at-risk (VaR) and conditional value-at-risk (CVaR) for energy price risk quantification in different emerging energy markets.We assess the best-fitting AR-exponential GARCH-EVT and AR-threshold GARCH-EVT models for Powernext and the European Energy Exchange, respectively. EVT is adopted explicitly to model the tails of the return distribution in order to capture extremal events. One of the main contributions of this paper is the estimation ofVaR and CVaR via EVT on the lower and upper tails of the return distribution in order to capture the extreme events of the distribution. This paper also contributes to the literature by analyzing both the upper and lower tails, in order to satisfy the different perspectives of regulators and investors in the energy market.

To continue reading...

You need to sign in to use this feature. If you don’t have a Risk.net account, please register for a trial.

Sign in
You are currently on corporate access.

To use this feature you will need an individual account. If you have one already please sign in.

Sign in.

Alternatively you can request an indvidual account here: