Second-order expansion for the maximum of some stationary Gaussian sequences
We prove a second-order approximation formula for the distribution of the largest term among an infinite moving average Gaussian sequence. The second-order correction term depends on the autocovariance function only through the second largest autocovariance. Applications to Gaussian time series are discussed and a simulation study showed a substantial improvement over other approximations to the exact distribution of the maximum.
Year of publication: |
2004
|
---|---|
Authors: | Barbe, Ph. ; McCormick, W. P. |
Published in: |
Stochastic Processes and their Applications. - Elsevier, ISSN 0304-4149. - Vol. 110.2004, 2, p. 315-342
|
Publisher: |
Elsevier |
Keywords: | Distribution of the maximum Gaussian sequence ARMA models Time series Second order |
Saved in:
Saved in favorites
Similar items by person
-
Barbe, Ph., (2011)
-
Barbe, Ph., (2011)
-
On the First-Order Edgeworth Expansion for a Markov Chain
Datta, S., (1993)
- More ...