Estimation of the mean of multivariate AR processes

In this paper, we show that for autoregressive processes the estimators of mean are consistent if the component of the process is ‘periodical’, and it is not the case if the component is a damping one. In the one-dimensional AR(1) case, the mean cannot be estimated well. In the complex AR(1), where...

Full description

Saved in:
Bibliographic Details
Published in:Computers & mathematics with applications (1987) 2002-03, Vol.43 (6), p.707-719
Main Authors: Arató, M., Pap, G., Varga, K.
Format: Article
Language:English
Subjects:
Autoregressive (AR) process
Maximum likelihood estimator
Weak stationarity
Wiener process
Citations: Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:In this paper, we show that for autoregressive processes the estimators of mean are consistent if the component of the process is ‘periodical’, and it is not the case if the component is a damping one. In the one-dimensional AR(1) case, the mean cannot be estimated well. In the complex AR(1), where the process behaves periodically, the mean can be estimated well. For an AR(2) process, the mean can be estimated well if the roots of the characteristic equation are complex.
ISSN:0898-1221
1873-7668
DOI:10.1016/S0898-1221(01)00315-7