Parameter Estimations in Linear Regression Models with AR(2) Errors in Which the Parameters Have a Special Relationship

Author

Xu, Wenke ; Liu, Fuxiang ; Li, Fengri ; Wu, Haijun ; Jin, Xuejing

Author_Institution

Northeast Forestry Univ., Harbin, China

fYear

2009

fDate

11-13 Dec. 2009

Firstpage

1

Lastpage

4

Abstract

The purpose of this paper is to study parameters estimations in linear regression model with AR(2) errors Â¿_t = Â¿₁Â¿_t-1 + Â¿₂Â¿_t-2 - Â¿_t, t = 1, 2,Â¿, n in which the parameters have a special relationship Â¿₂ = Â¿₁ ². For the properties of variance-covariance matrix Â¿ , This kind of models are transformed into the standard linear regression models without autocorrelation errors and apply the method of cycle generalized least squares (CGLS) to estimate parameters. Simulation results show that efficiency of CGLS method is superior over the method of generalized least squares (GLS) under mean square error criterion.

Keywords

parameter estimation; regression analysis; autocorrelation errors; cycle generalized least squares; linear regression model; mean square error criterion; parameter estimation; variance-covariance matrix; Autocorrelation; Covariance matrix; Equations; Gaussian processes; Least squares approximation; Least squares methods; Linear regression; Mean square error methods; Parameter estimation; Vectors;

fLanguage

English

Publisher

ieee

Conference_Titel

Computational Intelligence and Software Engineering, 2009. CiSE 2009. International Conference on

Conference_Location

Wuhan

Print_ISBN

978-1-4244-4507-3

Electronic_ISBN

978-1-4244-4507-3

Type

conf

DOI

10.1109/CISE.2009.5364199

Filename

5364199