Forecasting expected shortfall and value at risk with a joint elicitable mixed data sampling model

Qifa Xu, Lu Chen, Cuixia Jiang and Yezheng Liu

Journal of Forecasting, 2022, vol. 41, issue 3, 407-421

Abstract: Low‐frequency risk measures can filter out noise and better reflect the trend. In order to improve the forecasting accuracy of low‐frequency risk through making full use of the valuable information contained in high‐frequency independent variables, we propose a novel joint elicitable mixed data sampling (JE‐MIDAS) model by introducing MIDAS method into JE regression model. We utilize the JE‐MIDAS model to forecast value at risk and expected shortfall simultaneously and compare its performance with that of other popular models through both the Monte Carlo simulations and real‐world applications. The numerical results show that our model is superior to other models because it can model mixed‐frequency data directly, which avoids the information loss caused by frequency conversion. The empirical results on three stock indices also show that market volatility can increase financial risk. Interest rate has positive effects on risks for U.S. S&P500 and U.K. FTSE, whereas negative for SHCI of China.

Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
https://doi.org/10.1002/for.2817

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:41:y:2022:i:3:p:407-421

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 ().