Parameter Estimation for ARMA Models with Infinite Variance Innovations
Mikosch, Thomas ; Gadrich, Tamar ; Kluppelberg, Claudia ; Adler, Robert J.
Ann. Statist., Tome 23 (1995) no. 6, p. 305-326 / Harvested from Project Euclid
We consider a standard ARMA process of the form $\phi(B)X_t = \theta(B)Z_t$, where the innovations $Z_t$ belong to the domain of attraction of a stable law, so that neither the $Z_t$ nor the $X_t$ have a finite variance. Our aim is to estimate the coefficients of $\phi$ and $\theta$. Since maximum likelihood estimation is not a viable possibility (due to the unknown form of the marginal density of the innovation sequence), we adopt the so-called Whittle estimator, based on the sample periodogram of the $X$ sequence. Despite the fact that the periodogram does not, a priori, seem like a logical object to study in this non-$\mathscr{L}^2$ situation, we show that our estimators are consistent, obtain their asymptotic distributions and show that they converge to the true values faster than in the usual $\mathscr{L}^2$ case.
Publié le : 1995-02-14
Classification:  Stable innovations,  ARMA process,  periodogram,  Whittle estimator,  parameter estimation,  62M10,  62M15,  62E20,  62F10
@article{1176324469,
     author = {Mikosch, Thomas and Gadrich, Tamar and Kluppelberg, Claudia and Adler, Robert J.},
     title = {Parameter Estimation for ARMA Models with Infinite Variance Innovations},
     journal = {Ann. Statist.},
     volume = {23},
     number = {6},
     year = {1995},
     pages = { 305-326},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1176324469}
}
Mikosch, Thomas; Gadrich, Tamar; Kluppelberg, Claudia; Adler, Robert J. Parameter Estimation for ARMA Models with Infinite Variance Innovations. Ann. Statist., Tome 23 (1995) no. 6, pp.  305-326. http://gdmltest.u-ga.fr/item/1176324469/