Nonlinear Regression of Stable Random Variables
Jr, Clyde D. Hardin ; Samorodnitsky, Gennady ; Taqqu, Murad S.
Ann. Appl. Probab., Tome 1 (1991) no. 4, p. 582-612 / Harvested from Project Euclid
Let $(X_1, X_2)$ be an $\alpha$-stable random vector, not necessarily symmetric, with $0 < \alpha < 2$. This article investigates the regression $E(X_2 \mid X_1 = x)$ for all values of $\alpha$. We give conditions for the existence of the conditional moment $E(|X_2|^p|X_1 = x)$ when $p \geq \alpha$, and we obtain an explicit form of the regression $E(X_2 \mid X_1 = x)$ as a function of $x$. Although this regression is, in general, not linear, it can be linear even when the vector $(X_1, X_2)$ is skewed. We give a necessary and sufficient condition for linearity and characterize the asymptotic behavior of the regression as $x \rightarrow \pm \infty$. The behavior of the regression functions is also illustrated graphically.
Publié le : 1991-11-14
Classification:  Stable random vectors,  linear regression,  symmetric $\alpha$-stable,  60E07,  62J02,  60E10
@article{1177005840,
     author = {Jr, Clyde D. Hardin and Samorodnitsky, Gennady and Taqqu, Murad S.},
     title = {Nonlinear Regression of Stable Random Variables},
     journal = {Ann. Appl. Probab.},
     volume = {1},
     number = {4},
     year = {1991},
     pages = { 582-612},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1177005840}
}
Jr, Clyde D. Hardin; Samorodnitsky, Gennady; Taqqu, Murad S. Nonlinear Regression of Stable Random Variables. Ann. Appl. Probab., Tome 1 (1991) no. 4, pp.  582-612. http://gdmltest.u-ga.fr/item/1177005840/