Abstract
In 1973 Balestra examined the linear model y=XB+u, where u is a normally distributed disturbance vector, with variance matrix Ω. Ω has spectral decomposition\(\sum\limits_{i = 1}^r {\lambda _i M_i } \), and the matrices Mi are known.
Estimation of ω is thus equivalent with estimation of the λi. Balestra presented the best quadratic unbiased estimator of λi. In the present paper a derivation will be given which is based on a procedure developed by this writer (1980).
Similar content being viewed by others
References
Balestra, P.: Best quadratic unbiased estimators of the variance-covariance matrix in normal regression. Journal of Econometrics 1 (1973), 17–28.
Neudecker, H.: A comment on “Minimization of functions of a positive semidefinite matrix A subject to AX=0”. Journal of Multivariate Analysis 10 (1980), 135–139.
Rights and permissions
About this article
Cite this article
Neudecker, H. Best quadratic unbiased estimation of the variance matrix in normal regression. Statistische Hefte 21, 239–243 (1980). https://doi.org/10.1007/BF02932618
Issue Date:
DOI: https://doi.org/10.1007/BF02932618