Multivariate Asymmetric GARCH Model with Dynamic Correlation Matrix

This study examines the problem of modeling the joint dynamics of conditional volatility of several financial assets under an asymmetric relationship between volatility and shocks in returns (leverage effect). We propose a new multivariate asymmetric conditional heteroskedasticity model with a dynamic conditional correlation matrix (DCC-EGARCH). The proposed method allows modelling the joint dynamics of several financial assets taking into account the leverage effect in the financial markets. DCC-EGARCH model has two main advantages over previously proposed multivariate asymmetric specifications. It involves a substantially simpler optimization problem and does away with the assumption of conditional correlation time invariance. These features make the model more suitable for practical applications. To study the properties of the obtained estimators, we conducted a simulated data analysis. As a result, we found statistical evidence in favor of the developed DCC-EGARCH model compared with the symmetric DCC-GARCH process in case of considering data with the presence of the leverage effect. Further, we applied the proposed method to analyze the joint volatility of Rosneft stock returns and Brent oil prices. By estimating the DCC-EGARCH model, we found statistical evidence for both the presence of the leverage effect in the oil price data and the presence of the dynamic correlation structure between the time series, which motivates the practical application of the proposed method.

1. Markowitz H. Portfolio selection. The Journal of Finance. 1952;7(1):77–91. DOI: 10.1111/j.1540–6261.1952.tb01525.x

2. Sharpe W.F. Capital asset prices: A theory of market equilibrium under conditions of risk. The Journal of Finance. 1964;19(3):425–442. DOI: 10.1111/j.1540–6261.1964.tb02865.x

3. Miralles-Marcelo J.L., Miralles-Quirós J.L., Miralles-Quirós M. del M. Multivariate GARCH Models and risk minimizing portfolios: The importance of medium and small firms. The Spanish Review of Financial Economics. 2013;11(1):29–38. DOI: 10.1016/j.srfe.2013.03.001

4. Sia C.S., Chan F. Can multivariate GARCH models really improve value-at-risk forecasts? In: Proc. 21st Int. congr. on modelling and simulation (Gold Coast, Nov. 29-Dec. 04, 2015). Canberra: Modelling and Simulation Society of Australia and New Zealand Inc; 2015. DOI: 10.36334/MODSIM.2015.E 5.sia

5. Zhang X.F. Information uncertainty and stock returns. The Journal of Finance. 2006;61(1):105–137. DOI: 10.1111/j.1540–6261.2006.00831.x

6. Nelson D.B. Conditional heteroskedasticity in asset returns: A new approach. Econometrica. 1991;59(2):347–370. DOI: 10.2307/2938260

7. Black F. Studies of stock price volatility changes. In: Proc. 1976 Meet. Business and Economic Statistics Section, American Statistical Association. Alexandria, VA: ASA; 1976:177–181.

8. Christie A. The stochastic behavior of common stock variances: Value, leverage and interest rate effects. Journal of Financial Economics. 1982;10(4):407–432. DOI: 10.1016/0304–405X(82)90018–6

9. Kahneman D., Tversky A. Prospect theory: An analysis of decision under risk. Econometrica. 1979;47(2):263–292. DOI: 10.2307/1914185

10. Glosten L.R., Jagannathan R., Runkle D.E. On the relation between the expected value and the volatility of the nominal excess return on stocks. The Journal of Finance. 1993;48(5):1779–1801. DOI: 10.1111/j.1540–6261.1993.tb05128.x

11. Sentana E. Quadratic ARCH models. The Review of Economic Studies. 1995;62(4):639–661. DOI: 10.2307/2298081

12. Kroner K.F., Ng V.K. Modeling asymmetric comovements of asset returns. The Review of Financial Studies. 1998;11(4):817–844. DOI: 10.1093/rfs/11.4.817

13. Aftab H., Beg R.A., Sun S., Zhou Z. Testing and predicting volatility spillover — A multivariate GJR-GARCH approach. Theoretical Economics Letters. 2019;9(1):83–99. DOI: 10.4236/tel.2019.91008

14. Koutmos G., Booth G.G. Asymmetric volatility transmission in international stock markets. Journal of International Money and Finance. 1995;14(6):747–762. DOI: 10.1016/0261–5606(95)00031–3

15. Jane T. der, Ding C.G. On the multivariate EGARCH model. Applied Economics Letters. 2009;16(17):1757–1761. DOI: 10.1080/13504850701604383

16. Engle R. Dynamic conditional correlation: A simple class of multivariate generalized autoregressive conditional heteroskedasticity models. Journal of Business & Economic Statistics. 2002;20(3):339–350. DOI: 10.1198/073500102288618487 17. Newey W.K., McFadden D. Large sample estimation and hypothesis testing. In: Engle R.F., McFadden D.L., eds. Handbook of econometrics. Amsterdam: Elsevier Science B.V.; 1994;4:2111–2145. DOI: 10.1016/S 1573–4412(05)80005–4

17. Bollerslev T. Modelling the coherence in short-run nominal exchange rates: A multivariate generalized ARCH model. The Review of Economics and Statistics. 1990;72(3):498–505. DOI: 10.2307/2109358

18. Huang Y., Su W., Li X. Comparison of BEKK GARCH and DCC GARCH models: An empirical study. In: Proc. 6th Int. conf. on advanced data mining and applications (Chongqing, Nov. 19–21, 2010). Cham: Springer-Verlag; 2010:99–110. (Lecture Notes in Computer Science. Vol. 6441). DOI: 10.1007/978–3–642–17313–4_10

19. Orskaug E. Multivariate DCC-GARCH model — with various error distributions. Oslo: Norwegian Computing Center; 2009. 88 p. URL: http://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.417.5480&rep=rep1&type=pdf

20. Engle R.F., Kroner K.F. Multivariate simultaneous generalized ARCH. Econometric Theory. 1995;11(1):122–150. DOI: 10.1017/S0266466600009063

21. Engle R.F., Granger C.W.J., Kraft D. Combining competing forecasts of inflation using a bivariate arch model. Journal of Economic Dynamics and Control. 1984;8(2):151–165. DOI: 10.1016/0165–1889(84)90031–9

22. Bollerslev T., Engle R.F., Wooldridge J.M. A capital asset pricing model with time-varying covariances. Journal of Political Economy. 1988;96(1):116–131. DOI: 10.1086/261527

23. Engle R.F. Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflation. Econometrica. 1982;50(4):987–1007. DOI: 10.2307/1912773

24. Ghoudi K., Rémillard B. Comparison of specification tests for GARCH models. Computational Statistics & Data Analysis. 2014;76:291–300. DOI: 10.1016/j.csda.2013.03.009

25. Harrison B., Paton D. Do fat tails matter in GARCH estimation: Testing market efficiency in two transition economies. Economic Issues. 2007;12(2):15–26. URL: http://www.economicissues.org.uk/Files/207Harrison.pdf

26. Bollerslev T., Wooldridge J.M. Quasi-maximum likelihood estimation and inference in dynamic models with time-varying covariances. Econometric Reviews. 1992;11(2):143–172. DOI: 10.1080/07474939208800229