Abstract
In this empirical study, multifactor stochastic volatility models for the financial Nordic/Baltic power markets are developed, implemented, and analyzed. Stochastic volatility projections are the primary aim, followed by volatility forecasts and market repercussions. The research provides a functional variant of the conditional distribution (f(x|y)) based on conditional moments and a long-simulated state vector realization (MCMC-GMM) that is evaluated on observed data (a non-linear Kalman Filter) and applicable for step-forward volatility forecasts. For front year and quarter financial electricity contracts, the SV model creates two mean-reverting factors: one persistent and slowly moving component and one choppy, rapidly moving component. According to these factors, static volatility predictions with optimum and generous lags have a Theil covariance percentage of well over 97 percent for the front year contracts and 86 percent for the front quarter contracts. The volatility visibility and its associated static forecasts improve market transparency and will eventually make diversification and risk management easier to implement.
Subject
Energy (miscellaneous),Energy Engineering and Power Technology,Renewable Energy, Sustainability and the Environment,Electrical and Electronic Engineering,Control and Optimization,Engineering (miscellaneous)
Reference39 articles.
1. Stock Market Prices Do Not Follow Random Walks: Evidence from a Simple Specification Test
2. Financial returns modelled by the product of two stochastic processes–a study of daily sugarprices 1961-79;Taylor,1982
3. A subordinated stochastic process model with fixed variance for speculative prices;Clark;Econometrica,1973
4. The Pricing of Options on Assets with Stochastic Volatilities
5. Large Sample Properties of Generalized Method of Moments Estimators
Cited by
1 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献