The use of mixed copula functions in order to assess the degree and nature of the relationship of Russian stock market with foreign stock markets of developed and developing countries
Importance In the context of globalization and liberalization of financial markets, the mutual relations between the national stock markets become more relevant. Herewith decisions depend, and they were made regarding to the global diversification of the investment portfolio. Objectives The research aims to study the nature (asymmetries and powers) of the mutual relationships of the Russian stock market with foreign stock markets. Methods To achieve this goal, I have researched the parameters of the copula functions of the joint distribution of returns of indexes of the Russian and foreign stock markets and assessed the quality of approximation of functions of the joint distribution of the copula functions under study. To meet these challenges, I consider the model of mixed copulas (which is a function of making the transition from private distributions of random variables to their joint distribution). An estimation of the parameters using the mixed copulas is performed by the method of pseudomaximum likelihood. The private functions of distribution of returns of stock markets are set empirically. The study confirmed the changeable nature of the relationship of the Russian stock market with foreign stock markets of developed and developing countries. From January 2000 to May 2008, the relationship of the Russian stock market with most of the foreign stock markets has seen a left-handed bias. The period from June 2008 to December 2010 characterized by increased tightness of the relationship in both "tails" of the joint distribution of returns of stock markets. The third period (January, 2011 to March 2014) was characterized by the predominance of right-handed asymmetry in the Russian stock market relationship with the majority of the foreign stock markets. Mixed copulas in most cases have shown a better approximation to the function of the joint distribution of returns pairs of stock markets compared to simple copulas. Results The results suggest that mixed copula functions are more efficient modeling of the relationship of the stock markets with regard to the simple copulas. Conclusions and Relevance Mixed copulas may be applied when assessing the risks of investing in foreign stock, as well as to determine the optimal hedge ratio while hedging currency risks.
Keywords: copula, mixed copula, structure, interrelation, stock market, distribution function, global portfolio diversification
References:
Fantatstsini D. Modelirovanie mnogomernykh raspredelenii s ispol'zovaniem kopula-funktsii. Ch. 3 [Modeling multivariate distributions using copula functions]. Prikladnaya ekonometrika – Applied econometrics, 2011, no. 24, pp. 100–130.
Berg D. Copula goodness-of-fit testing: An overview and power comparison. The European Journal of Finance, 2009, no. 15, pp. 675–701.
Breymann W., Dias A., Embrechts P. Dependence structures for multivariate high-frequency data in finance. Quantitative Finance, 2003, no. 3, pp. 1–14.
Christoffersen P., Errunza V., et al. Is the potential for international diversification disappearing? A dynamic copula approach. Review of Financial Studies, 2012, no. 25, pp. 3711–3751.
Deheuvels P. La fonction de dependence empirique et ses proprietés: Un test non paramétriqued’indépendence. Bulletin de l’Académie Royale de Belgique, Classe des Sciences, 1979, no. 65, pp. 274–292.
Genest C., Ghoudi K., Rivest L. A Semiparametric Estimation Procedure for Dependence Parameters in Multivariate Families of Distributions. Biometrika, 1995, no. 82, pp. 543–552.
Genest С., Rémillard B., BeaudoinD. Goodness-of-fit tests for copulas: A review and a power study. Mathematics and Economics, 2009, no. 44, pp. 199–213.
Hennessy D. A., Lapan H. E. The use of archimedean copulas to model portfolio allocations. Mathematical Finance, 2002, no. 12, pp. 143.
Hu L. Dependence patterns across financial markets: a mixed copula approach. Applied Financial Economics, 2006, no. 16, pp. 717–729.
Lloyd S. Least square quantization in PCM’s. Bell Telephone Laboratories Paper, 1957.
Nelsen R. B. An introduction to copulas. Lecture Notes in Statistics, 2nd Edition. New York: Springer-Verlag, 2006.
Sklar A. Fonctions de répartition á n dimensions et leurs marges. Publ. Inst. Statis. Univ. Paris, 1959, no. 8, pp. 229–231.
Solnik B., Boucrelle C., Le Fur Y. International market correlation and volatility. Financial analysts journal, 2012, no. 52, pp. 17–34.
Tibiletti L. Beneficial changes in random variables via copulas: An application to insurance. The GENEVA Papers on Risk and Insurance Theory, 1995, no. 20, pp. 191–202.
Torres, J. M. Essays on international capital markets. ProQuest Dissertations and Theses, 2008.Available at: Link.
Turgutlu E., Ucer B. Is global diversification rational? Evidence from emerging equity markets through mixed copula approach. Applied Economics, 2010, no. 42, pp. 647–658.
