Asymptotic inference for AR(1) processes with (nonnormal) stable errors. IV. A note on the case of a negative unit root
Article
Abstract
In this note, we show that the limit distribution of the least-squares estimator in the case of a negative unit root is different from the limit distribution in the case of a positive unit root. Thus, the infinite-variance case is different from the finite-variance case.
Keywords
Unit Root Limit Distribution Sample Path Stable Process Stable Distribution
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
Preview
Unable to display preview. Download preview PDF.
References
- 1.L. Breiman,Probability, Addison-Wesley, Reading, Massachusetts (1968).Google Scholar
- 2.N. H. Chan and L. T. Tran, “On the first-order autoregressive process with infinite variance,”Econ. Theor.,5, 354–362 (1989).MathSciNetGoogle Scholar
- 3.J. L. Mijnheer,Sample Path Properties of Stable Processes, Mathematical Centre, Amsterdam (1975).Google Scholar
- 4.J. L. Mijnheer, “Asymptotic inference for AR(1) processes with (nonnormal) stable errors. I” (1995) (submitted).Google Scholar
- 5.J. L. Mijnheer, “Asymptotic inference for AR(1) processes with (nonnormal) stable errors. II, Properties of some stochastic integrals” (1995) (submitted).Google Scholar
- 6.J. L. Mijnheer, Asymptotic inference for AR(1) processes with (nonnormal) stable errors. III, Stable Ornstein-Uhlenbeck processes and integrals of stable O-U processes” (1996) (submitted).Google Scholar
- 7.G. Samorodnitsky and M. S. Taqqu,Stable Non-Gaussian Random Processes, Chapman & Hall, New York (1994).Google Scholar
Copyright information
© Plenum Publishing Corporation 1998