Back To Index Previous Article Next Article Full Text


Statistica Sinica 21 (2011), 1191-1200
doi:10.5705/ss.2009.066





TAIL BEHAVIOR AND OLS ESTIMATION

IN AR-GARCH MODELS


Theis Lange


University of Copenhagen


Abstract: The scope of this paper is twofold. We first describe the tail behavior for general AR-GARCH processes and hence extend the results of Basrak, Davis, and Mikosch (2002b) to another empirical relevant model class. Second, and primarily, we study properties for the OLS estimator in general AR-GARCH model. Specifically it is shown that the OLS estimator of the autoregressive parameter in the AR-GARCH model has a non-standard limiting distribution with a non-standard rate of convergence when the innovations have non-finite fourth order moment.



Key words and phrases: ARMA-GARCH, heavy tails, tail behavior.

Back To Index Previous Article Next Article Full Text