SearcharxivSearch

arXiv subjects

Philippe Bernardoff

Publications and source records attributed to Philippe Bernardoff.

3 recordsLinked to original sources

Simulations of multivariate gamma distributions and multifactor gamma distributions

This article provides a general expression for infinitely divisible multivariate gamma distributions defined by their Laplace transforms, as well as the conditional Laplace transform of infinitely divisible multivariate gamma distributions.We give algorithms for simulating infinitely divisible gamma distributions and infinitely divisible multifactor gamma distributions in dimension 2,3,4 and for all dimensions greater than 2 in the Markovian case. We give examples of simulations in dimension 2,3,4 and in dimension 5 in the Markovian case.

math.PR

Domain of existence of the Laplace transform of infinitely divisible negative multinomial distributions

This article provides the domain of existence $Ω$ of the Laplace transform of infinitely divisible negative multinomial distributions. We define a negative multinomial distribution on $\mathbb{N}^{n},$ where $\mathbb{N}$ is the set of nonnegative integers, by its probability generating function which will be of the form $\left( A\left( a_{1}z_{1} ,\ldots,a_{n}z_{n}\right) /A\left( a_{1},\ldots,a_{n}\right) \right) ^{-λ}$ where $A\left( \mathbf{z}\right) = {\displaystyle\sum\limits_{T\subset\left\{ 1,2,\ldots,n\right\} }} a_{T}\prod\limits_{i\in T}z_{i},$ where $a_{\emptyset}\neq0,$ and where $λ$ is a positive number. Finding couples $\left( A,λ\right) $ for which we obtain a probability generating function is a difficult problem. Necessary and sufficient conditions on the coefficients $a_{T}$ of $A$ for which we obtain a probability generating function for any positive number $λ$ are know by (Bernardoff, 2003). Thus we obtain necessary and sufficient conditions on $\mathbf{a}=\left( a_{1},\ldots,a_{n}\right) $ so that $\mathbf{a}=\left( \mathbf{e}^{t_{1}},\ldots,\mathbf{e}^{t_{n}}\right) $ with $\mathbf{t}=\left( t_{1},\ldots,t_{n}\right) $ belonging to $Ω$. This makes it possible to construct all the infinitely divisible multinomial distributions on $\mathbb{N}^{n}$. We give examples of construction in dimensions 2 and 3.

math.PR

Laplace copulas of multifactor gamma distributions are new generalized Farlie-Gumbel-Morgenstern copulas

This paper provides bifactor gamma distribution, trivariate gamma distribution and two copula families on [0, 1] n obtained from the Laplace transforms of the multivariate gamma distribution and the multi-factor gamma distribution given by [P ($θ$)] --$λ$ and [P ($θ$)] --$λ$ n i=1 (1 + pi$θ$i) --($λ$ i --$λ$) respectively, where P is an affine polynomial with respect to the n variables $θ$1,. .. , $θ$n. These copulas are new generalized Farlie-Gumbel-Morgenstern copulas and allow in particular to obtain multivariate gamma distributions for which the cumulative distribution functions and the probability distribution functions are known.

math.ST