Estimating value-at-risk for portfolios: skewed-EWMA forecasting via copula
Estimating value-at-risk for portfolios: skewed-EWMA forecasting via copula
With the increasing complexity of risks, how to estimate the risk of portfolios with complex dependencies is challenging. Recently, Lu and Huang (2007) proposed a skewed-b WMA procedure to calculate value-at-risk (VaR) for individual financial assets, which is derived from an asymmetric Laplace distribution and takes into account both skewness and heavy tails of the return distribution that are adaptive to the time-varying nature in practice by adjusting shape parameter in the distribution. In this paper, we extend the skewed-EWMA procedure to estimating the risk of complex portfolios with dependencies modelled via copula. Monte Carlo simulation procedure that combines copula techniques with skewed-EWMA forecasting is developed. The empirical backtesting evaluation of the VaR forecasting demonstrates that the proposed method can be a useful tool in estimating extreme risks of some complex portfolios.
87-115
Lu, Z.
4aa7d988-ac2b-4150-a586-ca92b8adda95
Li, S.
be6d14e4-0c49-47a8-a6e0-1c99a64e1024
2011
Lu, Z.
4aa7d988-ac2b-4150-a586-ca92b8adda95
Li, S.
be6d14e4-0c49-47a8-a6e0-1c99a64e1024
Lu, Z. and Li, S.
(2011)
Estimating value-at-risk for portfolios: skewed-EWMA forecasting via copula.
Australian Actuarial Journal, 17 (1), .
Abstract
With the increasing complexity of risks, how to estimate the risk of portfolios with complex dependencies is challenging. Recently, Lu and Huang (2007) proposed a skewed-b WMA procedure to calculate value-at-risk (VaR) for individual financial assets, which is derived from an asymmetric Laplace distribution and takes into account both skewness and heavy tails of the return distribution that are adaptive to the time-varying nature in practice by adjusting shape parameter in the distribution. In this paper, we extend the skewed-EWMA procedure to estimating the risk of complex portfolios with dependencies modelled via copula. Monte Carlo simulation procedure that combines copula techniques with skewed-EWMA forecasting is developed. The empirical backtesting evaluation of the VaR forecasting demonstrates that the proposed method can be a useful tool in estimating extreme risks of some complex portfolios.
This record has no associated files available for download.
More information
Published date: 2011
Organisations:
Mathematical Sciences
Identifiers
Local EPrints ID: 360474
URI: http://eprints.soton.ac.uk/id/eprint/360474
ISSN: 1442-3065
PURE UUID: 83129b22-c48e-4b47-80fd-bad01f1683c8
Catalogue record
Date deposited: 10 Dec 2013 14:41
Last modified: 11 Dec 2021 04:46
Export record
Contributors
Author:
S. Li
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics
