Accession Number : ADA134981

Title :   Asymptotic Properties of Extended Yule-Walker Estimates of the AR Parameters of an ARMA (Autoregressive Moving-Average).

Descriptive Note : Interim technical rept. Oct 82-May 83,

Corporate Author : NAVAL OCEAN SYSTEMS CENTER SAN DIEGO CA

Personal Author(s) : Gingras,D F

PDF Url : ADA134981

Report Date : 15 Jul 1983

Pagination or Media Count : 30

Abstract : The extended Yule-Walker equations are used to estimate the autoregressive parameters of an autoregressive moving-average time series. The asymptotic statistical properties of these estimates are derived. It is shown that they are asymptotically unbiased and normal; the covariance matrix of the limit distribution is calculated. The special case of estimating the autoregressive parameters of a noise corrupted autoregressive series is also treated. (Author)

Descriptors :   *Time series analysis, Asymptotic normality, Covariance, Matrices(Mathematics), Estimates, Theorems

Subject Categories : Statistics and Probability

Distribution Statement : APPROVED FOR PUBLIC RELEASE