Multivariate Pareto distribution

In statistics, a multivariate Pareto distribution is a multivariate extension of a univariate Pareto distribution.

There are several different types of univariate Pareto distributions including Pareto Types I−IV and Feller−Pareto. Multivariate Pareto distributions have been defined for many of these types.

Bivariate Pareto distributions

Bivariate Pareto distribution of the first kind

Mardia (1962) defined a bivariate distribution with cumulative distribution function (CDF) given by

F(x1,x2)=1−∑i=12(xiθi)−a+(∑i=12xiθi−1)−a,xi>θi>0,i=1,2;a>0,

and joint density function

f(x1,x2)=(a+1)a(θ1θ2)a+1(θ2x1+θ1x2−θ1θ2)−(a+2),xi≥θi>0,i=1,2;a>0.

The marginal distributions are Pareto Type 1 with density functions

f(xi)=aθiaxi−(a+1),xi≥θi>0,i=1,2.

The means and variances of the marginal distributions are

E[Xi]=aθia−1,a>1;Var(Xi)=aθi2(a−1)2(a−2),a>2;i=1,2,

and for a > 2, X1 and X2 are positively correlated with

cov⁡(X1,X2)=θ1θ2(a−1)2(a−2), and cor⁡(X1,X2)=1a.

Bivariate Pareto distribution of the second kind

Arnold suggests representing the bivariate Pareto Type I complementary CDF by

F‾(x1,x2)=(1+∑i=12xi−θiθi)−a,xi>θi,i=1,2.

If the location and scale parameter are allowed to differ, the complementary CDF is

F‾(x1,x2)=(1+∑i=12xi−μiσi)−a,xi>μi,i=1,2,

which has Pareto Type II univariate marginal distributions. This distribution is called a multivariate Pareto distribution of type II by Arnold. (This definition is not equivalent to Mardia's bivariate Pareto distribution of the second kind.)

For a > 1, the marginal means are

E[Xi]=μi+σia−1,i=1,2,

while for a > 2, the variances, covariance, and correlation are the same as for multivariate Pareto of the first kind.

Multivariate Pareto distributions

Multivariate Pareto distribution of the first kind

Mardia's Multivariate Pareto distribution of the First Kind has the joint probability density function given by

f(x1,…,xk)=a(a+1)⋯(a+k−1)(∏i=1kθi)−1(∑i=1kxiθi−k+1)−(a+k),xi>θi>0,a>0,(1)

The marginal distributions have the same form as (1), and the one-dimensional marginal distributions have a Pareto Type I distribution. The complementary CDF is

F‾(x1,…,xk)=(∑i=1kxiθi−k+1)−a,xi>θi>0,i=1,…,k;a>0.(2)

The marginal means and variances are given by

E[Xi]=aθia−1, for a>1, and Var(Xi)=aθi2(a−1)2(a−2), for a>2.

If a > 2 the covariances and correlations are positive with

cov⁡(Xi,Xj)=θiθj(a−1)2(a−2),cor⁡(Xi,Xj)=1a,i≠j.

Multivariate Pareto distribution of the second kind

Arnold suggests representing the multivariate Pareto Type I complementary CDF by

F‾(x1,…,xk)=(1+∑i=1kxi−θiθi)−a,xi>θi>0,i=1,…,k.

If the location and scale parameter are allowed to differ, the complementary CDF is

F‾(x1,…,xk)=(1+∑i=1kxi−μiσi)−a,xi>μi,i=1,…,k,(3)

which has marginal distributions of the same type (3) and Pareto Type II univariate marginal distributions. This distribution is called a multivariate Pareto distribution of type II by Arnold.

For a > 1, the marginal means are

E[Xi]=μi+σia−1,i=1,…,k,

while for a > 2, the variances, covariances, and correlations are the same as for multivariate Pareto of the first kind.

Multivariate Pareto distribution of the fourth kind

A random vector X has a k-dimensional multivariate Pareto distribution of the Fourth Kind if its joint survival function is

F‾(x1,…,xk)=(1+∑i=1k(xi−μiσi)1/γi)−a,xi>μi,σi>0,i=1,…,k;a>0.(4)

The k1-dimensional marginal distributions (k1<k) are of the same type as (4), and the one-dimensional marginal distributions are Pareto Type IV.

Multivariate Feller–Pareto distribution

A random vector X has a k-dimensional Feller–Pareto distribution if

Xi=μi+(Wi/Z)γi,i=1,…,k,(5)

where

Wi∼Γ(βi,1),i=1,…,k,Z∼Γ(α,1),

are independent gamma variables. The marginal distributions and conditional distributions are of the same type (5); that is, they are multivariate Feller–Pareto distributions. The one–dimensional marginal distributions are of Feller−Pareto type.