Construction of a bivariate copula by Rüschendorf’s method
Abstract
In this paper, a new copula model with given unit marginals is proposed, based on Rüschendorf’s Method. A new bivariate copula family is introduced by adding a proper term to independence copula. Thus, we avoid the complexity of the proposed copula model. By choosing a baseline copula from the same marginal, we derive a new copula that can approach from above towards the independence copula. Furthermore, it is established that a bivariate copula constructed by this method allows some flexibility in the dependence measure according to Spearman’s correlation coefficient. Additionally, tail dependence measures are investigated. Illustrative examples are given taking into account the specific choices of a baseline copula.
Keywords
Dependence, Rüschendorf’s method, Bivariate copula, Fréchet bounds, Spearman’s rho
References
- [1] Lai C. D., Xie M., A New Family of Positive Quadrant Dependent Bivariate Distributions, Statistics and Probability Letters, 46 (4) (2000) 359-364.
- [2] Bairamov I., Kotz S., Bekçi M., New generalized Farlie-Gumbel-Morgenstern distributions and concomitants of order statistics. Journal of Applied Statistics, 28 (5) (2001) 521-536.
- [3] Rüschendorf L., Construction of multivariate distributions with given marginals. Annals of the Institute of Statistical Mathematics, 37 (1985) 225-233.
- [4] Nelsen R. B., An Introduction to Copulas. Second Edition. Springer, New York (2006).
- [5] Asadian N., Amini M., Bozorgnia A. Some concepts of negative dependence for bivariate distributions with applications. Journal of Mathematical Extension, 4 (1) (2009) 43-59.
- [6] Hoeffding W., Masstabinvariante Korrelationstheorie, Schriften des Mathematischen Instituts und Instituts fur Angewandte Mathematik der Universitat Berlin, 5 (1940) 181-233.
- [7] Fréchet M., Sur Les Tableaux de Corrélation Dont Les marges Sont Donnees, Annales de l’Université de Lyon, Sciences 4 (1951) 13-84.
- [8] Schweizer B., Wolff E., On Nonparametric Measures of Dependence for Random Variables, The Annals of Statistics, 9(4) (1981) 879-885.
- [9] Farlie D., The Performance of Some Correlation Coefficients for a General Bivariate Distribution, Biometrika, 47 (3/4) (1960) 307-323.
- [10] Gumbel E. J., Bivariate Exponential Distributions, Journal of the American Statistical Association, 55 (292) (1960a) 698-707.