Shift‐contagion in energy markets and global crisis
Mehdi Mili,
Jean‐Michel Sahut and
Frédéric Teulon
Journal of Forecasting, 2020, vol. 39, issue 5, 725-736
Abstract:
This paper presents an analysis of shift‐contagion in energy markets, testing whether linkages between returns in energy markets increase during crisis periods. The research presented herein demonstrates how common movement between energy markets increases due to (i) shift‐contagion across energy markets, reflected by structural transmission of shocks across markets and (ii) larger common shocks operating through standard cross‐market interdependences. A regime‐switching model was developed to detect shift‐contagion across energy markets. In the approach adopted herein, the occurrence of shift‐contagion is endogenously estimated rather than being exogenously assigned. The results show that shift‐contagion has been a major feature of energy markets over the last decade. Evidence is presented which demonstrates that the linkages between energy markets do not appear to be stable. These results are remarkably accurate for forecasting Brent and natural gas for horizons for up to 50 days. Conversely, for WTI (West Texas Intermediate oil) and coal, the model performs well only for forecasting very short horizons (up to 20 days). For all products, the model shows significant biases for long horizons.
Date: 2020
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (2)
Downloads: (external link)
https://doi.org/10.1002/for.2654
Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.
Export reference: BibTeX
RIS (EndNote, ProCite, RefMan)
HTML/Text
Persistent link: https://EconPapers.repec.org/RePEc:wly:jforec:v:39:y:2020:i:5:p:725-736
Access Statistics for this article
Journal of Forecasting is currently edited by Derek W. Bunn
More articles in Journal of Forecasting from John Wiley & Sons, Ltd.
Bibliographic data for series maintained by Wiley Content Delivery ().