On Lévy measures for infinitely divisible natural exponential families
We link the infinitely divisible measure [mu] to its modified Lévy measure [rho]=[rho]([mu]) in terms of their variance functions, where x-2[[rho](dx)-[rho]({0})[delta]0(dx)] is the Lévy measure associated with [mu]. We deduce that, if the variance function of [mu] is a polynomial of degree p[greater-or-equal, slanted]2, then, the variance function of [rho] is still a second degree polynomial. We illustrate these results with some Lévy processes such as positive stable and a class of Poisson stopped-sum processes.
| Year of publication: |
2006
|
|---|---|
| Authors: | Kokonendji, Célestin C. ; Khoudar, Mohamed |
| Published in: |
Statistics & Probability Letters. - Elsevier, ISSN 0167-7152. - Vol. 76.2006, 13, p. 1364-1368
|
| Publisher: |
Elsevier |
| Keywords: | Compound Poisson process Laplace transform Lévy process Stable process Variance function |
Saved in:
Saved in favorites
Similar items by person
-
Bayesian estimation of adaptive bandwidth matrices in multivariate kernel density estimation
Zougab, Nabil, (2014)
-
Kokonendji, Célestin C., (2010)
-
On the Monge–Ampère equation for characterizing gamma-Gaussian model
Kokonendji, Célestin C., (2013)
- More ...