Large and moderate deviations upper bounds for the Gaussian autoregressive process
β Scribed by Julien Worms
- Publisher
- Elsevier Science
- Year
- 2001
- Tongue
- English
- Weight
- 108 KB
- Volume
- 51
- Category
- Article
- ISSN
- 0167-7152
No coin nor oath required. For personal study only.
β¦ Synopsis
We study the least-squares estimator in the scalar autoregressive model of order 1 with Gaussian noise and arbitrary ΓΏxed initial state. Upper bounds of both large and moderate deviations principles are achieved in the unstable and explosive frameworks. The moderate deviations results are consistent with known results of convergence in distribution of the literature.
π SIMILAR VOLUMES
In this paper we prove large and moderate deviations results for certain sequences of mixtures of probability measures. These results give large and moderate deviations for the empirical measures of an exchangeable sequence. (~) 1997 Elsevier Science B.V.