thumbnail

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

Regional Science and Urban Economics

By:
,

Links

  • The Publications Warehouse does not have links to digital versions of this publication at this time

Abstract

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.

Additional Publication Details

Publication type:
Article
Publication Subtype:
Journal Article
Title:
Experiments with central-limit properties of spatial samples from locally covariant random fields
Series title:
Regional Science and Urban Economics
Volume
22
Issue:
3
Year Published:
1992
Language:
English
Larger Work Type:
Article
Larger Work Subtype:
Journal Article
First page:
387
Last page:
403
Number of Pages:
17