You are here:
EFFICIENCY OF LEAST SQUARES ESTIMATORS IN THE PRESENCE OF SPATIAL AUTOCORRELATION
Citation:
Cordy, C. AND D. Griffith. EFFICIENCY OF LEAST SQUARES ESTIMATORS IN THE PRESENCE OF SPATIAL AUTOCORRELATION. U.S. Environmental Protection Agency, Washington, D.C., EPA/600/J-94/098.
Description:
The authors consider the effect of spatial autocorrelation on inferences made using ordinary least squares estimation. it is found, in some cares, that ordinary least squares estimators provide a reasonable alternative to the estimated ' generalized least squares estimators recommended in the spatial statistics literature. ne of the most serious problems in using ordinary least squares is that the usual variance estimators are severely biased when the errors are correlated. n alternative variance estimator that adjusts for any observed correlation is proposed. he need to take autocorrelation into account in variance estimation negates much of the advantage that ordinary least squares estimation has in terms of computation simplicity.