The Annals of Statistics

Asymptotically Efficient Estimators for a Constant Regression with Vector- Valued Stationary Residuals

Rolf K. Adenstedt

Full-text: Open access

Abstract

Estimation of linear functions of a vector parameter $\theta$ when an observed discrete- or continuous-time vector-valued stationary process has mean value $H\theta, H$ a known matrix, is considered. Large-sample comparisons of best linear unbiased estimators and estimators based on the sample mean are made. Limits and rates of convergence of the variances of these estimators are obtained. It is shown that under general conditions there are asymptotically efficient estimators based on the sample mean, their form determined by the spectrum at the origin. Conditions under which all least squares estimators are asymptotically efficient are also given.

Article information

Source
Ann. Statist., Volume 3, Number 5 (1975), 1109-1121.

Dates
First available in Project Euclid: 12 April 2007

Permanent link to this document
https://projecteuclid.org/euclid.aos/1176343243

Digital Object Identifier
doi:10.1214/aos/1176343243

Mathematical Reviews number (MathSciNet)
MR375697

Zentralblatt MATH identifier
0318.62046

JSTOR
links.jstor.org

Subjects
Primary: 62M10: Time series, auto-correlation, regression, etc. [See also 91B84]
Secondary: 62J05: Linear regression

Keywords
Linear estimation regression stationary vector-valued processes asymptotic efficiency spectral representations Moore-Penrose pseudoinverse

Citation

Adenstedt, Rolf K. Asymptotically Efficient Estimators for a Constant Regression with Vector- Valued Stationary Residuals. Ann. Statist. 3 (1975), no. 5, 1109--1121. doi:10.1214/aos/1176343243. https://projecteuclid.org/euclid.aos/1176343243


Export citation