A Comparison Between Maximum Likelihood and Generalized Least Squares in a Heteroscedastic Linear Model

1 December 1982

journal article
research article
Published by JSTOR in Journal of the American Statistical Association

Vol. 77 (380) , 878
https://doi.org/10.2307/2287321

Abstract

We consider a linear model with normally distributed but heteroscedastic errors. When the error variances are functionally related to the regression parameter, one can use either maximum likelihood or generalized least squares to estimate the regression parameter. We show that likelihood is more sensitive to small misspecifications in the functional relationship between the error variances and the regression parameter.

Keywords

LINEAR MODELS
HETEROSCEDASTICITY
CONTIGUITY
ROBUSTNESS
WEIGHTED LEAST SQUARES
MAXIMUM LIKELIHOOD

This publication has 0 references indexed in Scilit: