Autoregressive processes with infinite variance
- 1 June 1977
- journal article
- Published by Cambridge University Press (CUP) in Journal of Applied Probability
- Vol. 14 (2) , 411-415
- https://doi.org/10.2307/3213015
Abstract
The least squares estimators βi(N), j = 1, …, p, from N data points, of the autoregressive constants for a stationary autoregressive model are considered when the disturbances have a distribution attracted to a stable law of index α < 2. It is shown that N1/δ(βi(N) – β) converges almost surely to zero for any δ > α. Some comments are made on alternative definitions of the βi(N).Keywords
This publication has 7 references indexed in Scilit:
- On quotients of moving average processes with infinite meanProceedings of the American Mathematical Society, 1976
- Regression and autoregression with infinite varianceAdvances in Applied Probability, 1974
- Regression and autoregression with infinite varianceAdvances in Applied Probability, 1974
- Multiple Time SeriesWiley Series in Probability and Statistics, 1970
- An $L^p$-Convergence TheoremThe Annals of Mathematical Statistics, 1969
- A Note on Sums of Independent Random Variables with Infinite First MomentThe Annals of Mathematical Statistics, 1967
- The null distribution of the first serial correlation coefficientBiometrika, 1966