• DocumentCode
    3096727
  • Title

    Approximate AR modeling: a Schur approach

  • Author

    Pal, Debajyoti ; Kailath, Thomas

  • Author_Institution
    AT&T Bell Labs., Middletown, NJ, USA
  • fYear
    1990
  • fDate
    10-12 Oct. 1990
  • Firstpage
    275
  • Lastpage
    279
  • Abstract
    Based on a new Schur type algorithm for factorization and inversion of Toeplitz and quasi-Toeplitz matrices with arbitrary rank profile, a new approach towards approximate autoregressive modeling has been developed. This technique provides an alternative to the well known regularization scheme for covariance matrices with one or more nearly zero minors.<>
  • Keywords
    matrix algebra; spectral analysis; statistical analysis; Schur type algorithm; Toeplitz matrices; approximate AR modeling; approximate autoregressive modeling; factorization; inversion; quasi-Toeplitz matrices; spectral analysis; Approximation algorithms; Contracts; Ear; Equations; Polynomials;
  • fLanguage
    English
  • Publisher
    ieee
  • Conference_Titel
    Spectrum Estimation and Modeling, 1990., Fifth ASSP Workshop on
  • Conference_Location
    Rochester, NY, USA
  • Type

    conf

  • DOI
    10.1109/SPECT.1990.205590
  • Filename
    205590
    • Link To Document
    https://search.isc.ac/dl/search/defaultta.aspx?DTC=49&DC=3096727