Evaluating electricity price volatility risk in competitive environment based on ARMAX-GARCHSK-EVT model Online publication date: Sat, 07-Feb-2015
by Jin Wang; Ruiqing Wang
International Journal of Computer Applications in Technology (IJCAT), Vol. 50, No. 3/4, 2014
Abstract: Effectively evaluating volatility of price risk is the foundation of risk management in competitive environments. Considering the natures of electricity prices, a two-stage model for estimating value-at-risk (VaR) based on ARMAX-GARCHSK and extreme value theory (EVT) is proposed. First, an ARMAX-GARCHSK model, which can capture the most important characteristics of electricity price series, such as seasonalities, heteroscedasticities, skewnesses and lepkurtosises, is used to filter electricity price series. In this way, an approximately independently and identically distributed normalised residual series is acquired. Then EVT is adopted to explicitly model the tails of the standardised residuals of ARMAX-GARCHSK model, and accurate estimates of VaR in electricity market can be yielded. The empirical analysis suggests that the ARMAX-GARCHSK-EVT model can rapidly reflect the recent and relevant changes of electricity prices and produce more accurate forecasts of VaR at all confidence levels, showing better dynamic characteristics. These results present several potential implications for electricity market risk quantifications and hedging strategies.
Existing subscribers:
Go to Inderscience Online Journals to access the Full Text of this article.
If you are not a subscriber and you just want to read the full contents of this article, buy online access here.Complimentary Subscribers, Editors or Members of the Editorial Board of the International Journal of Computer Applications in Technology (IJCAT):
Login with your Inderscience username and password:
Want to subscribe?
A subscription gives you complete access to all articles in the current issue, as well as to all articles in the previous three years (where applicable). See our Orders page to subscribe.
If you still need assistance, please email subs@inderscience.com