Skip to main content
U.S. flag

An official website of the United States government

Experiments with central-limit properties of spatial samples from locally covariant random fields

January 1, 1992

When spatial samples are statistically dependent, the classical estimator of sample-mean standard deviation is well known to be inconsistent. For locally dependent samples, however, consistent estimators of sample-mean standard deviation can be constructed. The present paper investigates the sampling properties of one such estimator, designated as the tau estimator of sample-mean standard deviation. In particular, the asymptotic normality properties of standardized sample means based on tau estimators are studied in terms of computer experiments with simulated sample-mean distributions. The effects of both sample size and dependency levels among samples are examined for various value of tau (denoting the size of the spatial kernel for the estimator). The results suggest that even for small degrees of spatial dependency, the tau estimator exhibits significantly stronger normality properties than does the classical estimator of standardized sample means. ?? 1992.

Citation Information

Publication Year 1992
Title Experiments with central-limit properties of spatial samples from locally covariant random fields
Authors T. H. Barringer, T. E. Smith
Publication Type Article
Publication Subtype Journal Article
Series Title Regional Science and Urban Economics
Index ID 70017284
Record Source USGS Publications Warehouse