The relative efficiency of OLS in the linear regression model with spatially autocorrelated errors
The relative efficiency of the OLS-estimator in the linear regression model given spatially autocorrelated errors is considered. A theorem of Krämer and Donninger (1987) is shown to be wrong and a corrected proof of this result is given under an additional assumption.
KeywordsSpatial Autocorrelation Weighting Matrix Linear Regression Model Relative Efficiency Corrected Proof
Unable to display preview. Download preview PDF.
- Anselin, L. (1988): Spatial Econometrics: Methods and Models, Kluwer Academic Publishers, Dordrecht.Google Scholar
- Cliff, A. D., and J. K. Ord (1973): Spatial Autocorrelation, Pion, London.Google Scholar
- Miron, J. (1984): “Spatial Autocorrelation in Regression Analysis: A Beginner's Guide”, in: Spatial Statistics and Models, Eds. Gaile, G. L. und C. J. Willmott, D. Reidel Publishing Company, Dordrecht, 201–222.Google Scholar
- Rao, C. R. (1967): “Least Squares Theory Using an Estimated Dispersion Matrix and Its Application to the Measurement of Signals”, in: Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability (Volume 1), Eds. LeCam, L. and J. Neyman, University of California Press, Berkeley, 355–372.Google Scholar