Asymptotic normality of high level-large time crossings of a Gaussian process

From MaRDI portal
Publication:2419974



Abstract: We prove the asymptotic normality of the standardized number of crossings of a centered stationary mixing Gaussian process when both the level and the time horizon go to infinity in such a way that the expected number of crossings also goes to infinity.


This paper studies the asymptotic behavior for the number of up-crossings of a mean zero and variance one stationary Gaussian process with smooth paths through a level \(u\) over a time interval \([0, T]\). When \(u\) and \(T\) both go to infinity in such a way that the expectation of the number of crossings remains fixed, it was shown that the normalized number of crossings asymptotically behaves like a standardized Poisson process where the intensity is the constant expectation of the number of up-crossings [\textit{V. A. Volkonskij} and \textit{Yu. A. Rozanov}, Theory Probab. Appl. 4, 178--197 (1959; Zbl 0092.33502); translation from Teor. Veroyatn. Primen. 4, 186--207 (1959); \textit{V. A. Volkonskij} and \textit{Yu. A. Rozanov}, Theory Probab. Appl. 6, 186--198 (1962; Zbl 0108.31301); translation from Teor. Veroyatn. Primen. 6, 202--215 (1961)]. The asymptotic normality of the number of crossings is proved in this paper when the expected number of crossings also goes to infinity. The basic in the proof is the Bernstein block method for dependent random variables in the Central Limit Theorem with the formulation presented in [\textit{J.-M. Bardet} et al., ESAIM, Probab. Stat. 12, 154--172 (2008; Zbl 1187.60013)].











This page was built for publication: Asymptotic normality of high level-large time crossings of a Gaussian process

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2419974)