Bitte verwenden Sie diesen Link, um diese Publikation zu zitieren, oder auf sie als Internetquelle zu verweisen: https://hdl.handle.net/10419/258614 
Autor:innen: 
Erscheinungsjahr: 
2021
Quellenangabe: 
[Journal:] Journal of Risk and Financial Management [ISSN:] 1911-8074 [Volume:] 14 [Issue:] 11 [Article No.:] 510 [Publisher:] MDPI [Place:] Basel [Year:] 2021 [Pages:] 1-17
Verlag: 
MDPI, Basel
Zusammenfassung: 
This paper builds and implements multifactor stochastic volatility models for the international oil/energy markets (Brent oil and WTI oil) for the period 2011-2021. The main objective is to make step ahead volatility predictions for the front month contracts followed by an implication discussion for the market (differences) and observed data dependence important for market participants, implying predictability. The paper estimates multifactor stochastic volatility models for both contracts giving access to a long-simulated realization of the state vector with associated contract movements. The realization establishes a functional form of the conditional distributions, which are evaluated on observed data giving the conditional mean function for the volatility factors at the data points (nonlinear Kalman filter). For both Brent and WTI oil contracts, the first factor is a slow-moving persistent factor while the second factor is a fast-moving immediate mean reverting factor. The negative correlation between the mean and volatility suggests higher volatilities from negative price movements. The results indicate that holding volatility as an asset of its own is insurance against market crashes as well as being an excellent diversification instrument. Furthermore, the volatility data dependence is strong, indicating predictability. Hence, using the Kalman filter from a realization of an optimal multifactor SV model visualizes the latent step ahead volatility paths, and the data dependence gives access to accurate static forecasts. The results extend market transparency and make it easier to implement risk management including derivative trading (including swaps).
Schlagwörter: 
energy
forecasting volatility
Markov Chain Monte Carlo (MCMC) simulations
projection-reprojection
stochastic volatility models
Persistent Identifier der Erstveröffentlichung: 
Creative-Commons-Lizenz: 
cc-by Logo
Dokumentart: 
Article

Datei(en):
Datei
Größe





Publikationen in EconStor sind urheberrechtlich geschützt.