An EM Algorithm for Multivariate NIG Distribution and its Application to Value-at-Risk

10.6186/IJIMS.2010.21.3.3

Yi-Ping Chang；Ming-Chin Hung；Szu-Fang Wang；Chih-Tun Yu

Multivariate Normal-Inverse Gaussian Distribution ； EM Algorithm ； Value-at-Risk

International Journal of Information and Management Sciences

21：3（2010 / 09 / 01）

265 - 284

英文

Many empirical studies show that the normal-inverse Gaussian (NIG) distribution allows a realistic description of asset returns. This paper deals with the maximum likelihood estimation (MLE) of parameters of the multivariate NIG (MNIG) distribution. Due to the complexity of the likelihood, direct optimization is difficult and inefficient. An expectationmaximization (EM) algorithm is proposed to compute the MLE of the MNIG parameters. This paper also deals with the Value-at-Risk (VaR) estimation for portfolio return under the MNIG distribution. In addition, a simulation study is carried out for the performance of VaR estimations, and the EM algorithm serves as an efficient way to compute portfolio VaR in the cases of the tail behavior of asset return.

1. Karlis, D. and Papadimitriou, A., Inference for the multivariate normal inverse Gaussian model, http://www.stat-athens.aueb.gr/ esi/proceedings/17/esi17-p511.pdf, 2004.
2. Barndorff-Nielsen, O. E.(1997).Normal inverse Gaussian distributions and stochastic volatility modeling.Scandinavian Journal of Statistics,24(1),1-13.
3. Barndorff-Nielsen, O. E.(1998).Processes of normal inverse Gaussian type.Finance and Stochastics,2(1),41-68.
4. Barndorff-Nielsen, O. E.,Prause, K.(2001).Apparent scaling.Finance and Stochastics,5(1),103-113.
5. Chhikara, R. S.,Folks, J. L.(1989).The Inverse Gaussian Distribution: Theory, Methodology and Application.New York:Marcel Dekker.
6. Dempster, A.P.,Laird, N. M.,Rubin, D.(1977).Maximum likelihood from incomplete data via the EM algorithm.Journal of the Royal Statistical Society B,39(1),1-38.
7. Huang, H. H.,Liu, Y. H.,Huang, W. T.(2009).Marginal maximum likelihood estimators for ranked means in exponential families.International Journal of Information and Management Sciences,20(3),469-489.
8. Jorion, P.(2006).Value at Risk: The New Benchmark for Managing Financial Risk.New York:McGraw-Hill.
9. Karlis, D.(2002).An EM type algorithm for maximum likelihood estimation of the normal-inverse Gaussian distribution.Statistics and Probability Letters,57(1),43-52.
10. Lillestöl, J.(2000).Risk analysis and the NIG distribution.Journal of Risk,2(4),41-55.
11. McNeil, A.J.,Frey, R.,Embrechts, P.(2006).Quantitative Risk Management: Concepts, Techniques, and Tools.Princeton:Princeton University Press.
12. Øigård, T. A.,Hanssen, A.,Hansen, R. R.,Godtliebsen, F.(2005).EM-estimation and modeling of heavy tailed processes with the multivariate normal inverse Gaussian distribution.Signal Processing,85(8),1655-1673.
13. Protassov, R. S.(2004).EM-based maximum likelihood parameter estimation for multivariate generalized hyperbolic distributions with fixed λ.Statistics and Computing,14(1),67-77.
14. Venter, J. H.,de Jongh, P. J.(2004).Selecting an innovation distribution for Garch models to improve efficiency of risk and volatility estimation.Journal of Risk,6(3),27-52.
15. Venter, J. H.,de Jongh, P. J.(2002).Risk estimation using the normal inverse Gaussian distribution.Journal of Risk,4(2),1-23.
16. Wu, C. C.,Wu, S. F.,Chan, H. Y.(2004).MLE and the estimated expected test time for Pareto distribution under progressive censoring data.International Journal of Information and Management Sciences,15(3),29-42.
17. Wu, S. J.,Chang, C. T.(2002).Parameter estimations based on exponential progressive type II censored data with binomial removals.International Journal of Information and Management Sciences,13(3),37-46.

1. Yu, Chih-Tun,Liu, Huimei,Chang, Yi-Ping(2011).Bayesian Inference for Credit Risk with Serially Dependent Factor Model.International Journal of Information and Management Sciences,22(2),135-155.