Copula (statistics)
From Wikipedia, the free encyclopedia
In statistics, a copula is a multivariate cumulative distribution function defined on the n-dimensional unit cube [0, 1]n such that every marginal distribution is uniform on the interval [0, 1].
The copula contains all of the information on the nature of the dependence between the two random variables that can be given without the marginal distributions, but gives no information on the marginal distributions. In effect the information on the marginals and the information on the dependence are neatly separated from each other.
Some copula properties are the following:
- <math>C(u,0)=C(0,v)=0\,</math>
- <math>C(u,1)=u; \qquad C(1,v)=v.</math>
Contents |
[edit] Sklar's theorem
The theorem proposed by Sklar <ref name="Sklar 1959">Sklar (1959)</ref> underlies most applications of the copula. Sklar's theorem states that given a joint distribution function H for p variables, and respective marginal distribution functions, there exists a copula C such that the copula binds the margins to give the joint distribution.
For the bivariate case, Sklar's theorem can be stated as follows. For any bivariate distribution function H(x, y), let F(x) = H(x, (-∞,∞)) and G(y) = H((-∞,∞), y) be the univariate marginal probability distribution functions. Then there exists a copula C such that
- <math>H(x,y)=C(F(x),G(y))\,</math>
(where we have identified the distribution C with its cumulative distribution function). Moreover, if marginal distributions, say, F(x) and G(y), are continuous, the copula function C is unique. Otherwise, the copula C is unique on the range of values of the marginal distributions.
[edit] Fréchet-Hoeffding copula boundaries
Minimum copula: This is the lower bound for all copulas. In the bivariate case only, it represents perfect negative dependence between variates.
- <math> W(u,v) = \max(0,u+v-1).\,</math>
Maximum copula: This is the upper bound for all copulas. It represents perfect positive dependence between variates:
- <math> M(u,v) = \min(u,v).\,</math>
Thus, for all copulas <math>C(u,v)</math>,
- <math> W(u,v) \le \; C(u,v) \le \; M(u,v)</math>
[edit] Gaussian copula
One example of a copula often used for modelling in finance is the Gaussian Copula, which is constructed from the bivariate normal distribution via Sklar's theorem. For X and Y distributed as standard bivariate normal with correlation ρ the Gaussian copula function is
- <math> C_\rho(u,v) = \Phi_{U,V, \rho} \left(\Phi^{-1}(u), \Phi^{-1}(v) \right) </math>
where the marginals of U and V are N(0,1) distributions and Φ denotes the cumulative normal density. Differentiating this yields
- <math> c_\rho(u,v) = \frac{\phi_{U,V, \rho} (\Phi_X^{-1}(u), \Phi_Y^{-1}(v) )}
{\phi(\Phi^{-1}(u)) \phi(\Phi^{-1}(v))}</math>
where
- <math> \phi_{X,Y, \rho}(x,y) = \frac{1}{2 \pi\sqrt{1-\rho^2}} \exp \left (-
\frac{1}{2(1-\rho^2)} \left [{x^2+y^2} -2\rho xy \right ] \right ) </math>
is the density function for the bivariate normal variate with Pearson's product moment correlation coefficient <math>\rho</math>, φ is the density of the N(0,1) distribution (the marginal density).
[edit] Archimedean copulas
One particularly simple form of a copula is
- <math> H(x,y) = \Psi^{-1}(\Psi(F(x))+\Psi(G(y)))\,</math>
where <math>\psi</math> is known as a generator function. Such copulas are known as Archimedean. Any generator function which satisfies the properties below is the basis for a valid copula:
- <math>\Psi(1) = 0;\qquad \lim_{x \to 0}\Psi(x) = \infty;\qquad \Psi'(x) < 0;\qquad \Psi(x) > 0. </math>
Product copula: Also called the independent copula, this copula has no dependence between variates. Its density function is unity everywhere.
- <math>\Psi(x) = -\ln(x); \qquad H(x,y) = xy.</math>
Where the generator function is indexed by a parameter, a whole family of copulas may be Archimedean. For example:
Clayton copula:
- <math>\Psi(x) = x^{\theta} -1;\qquad \theta \le 0; \qquad H(x,y) = (F(x)^\theta+G(y)^\theta-1)^{1/\theta}.</math>
For θ = 0 in the Clayton copula, the random variables are statistically independent. The generator function approach can be extended to create multivariate copulas, by simply including more additive terms.
[edit] References
[edit] Notes
<references/>
[edit] General
- David G. Clayton (1978), "A model for association in bivariate life tables and its application in epidemiological studies of familial tendency in chronic disease incidence", Biometrika 65, 141-151. JSTOR (subscription)
- Frees, E.W., Valdez, E.A. (1998), "Understanding Relationships Using Copulas", North American Actuarial Journal 2, 1-25. Link to NAAJ copy
- Roger B. Nelsen (1999), An Introduction to Copulas. ISBN 0-387-98623-5.
- S. Rachev, C. Menn, F. Fabozzi (2005), Fat-Tailed and Skewed Asset Return Distributions. ISBN 0-471-71886-6.
- A. Sklar (1959), "Fonctions de répartition à n dimensions et leures marges", Publications de l'Institut de Statistique de L'Université de Paris 8, 229-231.
- W.T. Shaw, K.T.A. Lee (2006), "Copula Methods vs Canonical Multivariate Distributions: The Multivariate Student T Distibution with General Degrees of Freedom". PDF
