• DocumentCode
    2031375
  • Title

    Large deviations for quadratic forms of Gaussian stationary processes with applications

  • Author

    Bercu, B. ; Gamboa, F. ; Rouault, A.

  • Author_Institution
    Lab. de Stat., Univ. de Paris-Sud, Orsay, France
  • Volume
    1
  • fYear
    1997
  • fDate
    10-12 Dec 1997
  • Firstpage
    594
  • Abstract
    We establish a large deviation principle for Toeplitz quadratic forms of stationary Gaussian processes. We also propose some statistical applications such as the large deviation behavior of the least squares and the Yule-Walker estimators of the parameter of the autoregressive stable Gaussian process
  • Keywords
    Gaussian processes; Toeplitz matrices; autoregressive processes; least squares approximations; parameter estimation; Gaussian stationary processes; Toeplitz quadratic forms; Yule-Walker estimators; autoregressive stable Gaussian process; large deviation behavior; least squares estimators; stationary Gaussian processes; Content addressable storage; Convergence; Eigenvalues and eigenfunctions; Gaussian processes; Least squares approximation; Level set; Parameter estimation; White noise;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Decision and Control, 1997., Proceedings of the 36th IEEE Conference on
  • Conference_Location
    San Diego, CA
  • ISSN
    0191-2216
  • Print_ISBN
    0-7803-4187-2
  • Type

    conf

  • DOI
    10.1109/CDC.1997.650695
  • Filename
    650695