Least Squares Estimation when the Covariance Matrix and Parameter Vector are Functionally Related
- 1 March 1980
- journal article
- research article
- Published by JSTOR in Journal of the American Statistical Association
- Vol. 75 (369) , 176
- https://doi.org/10.2307/2287408
Abstract
Estimation for the linear model y = Xβ + e with unknown diagonal covariance matrix G is considered. The diagonal elements of G are assumed to be known functions of the explanatory variables X and an unknown parameter vector Θ, where Θ is permitted to contain elements of β. A weighted joint least squares estimator is developed that is asymptotically equivalent to the maximum likelihood estimator. Asymptotic properties of the simple least squares estimator and of the weighted joint least squares estimator are obtained. A sampling experiment is used to compare the estimators.Keywords
This publication has 0 references indexed in Scilit: