Spatio-temporally correlated data appear in many environmental studies, and consequently, there is an increasing demand for estimation methods that take account of spatio-temporal (ST) correlation and thereby improve ...
详细信息
Spatio-temporally correlated data appear in many environmental studies, and consequently, there is an increasing demand for estimation methods that take account of spatio-temporal (ST) correlation and thereby improve the accuracy of estimation. In this paper, we propose an estimation procedure that improves efficiency, which is based upon a nonparametric pre-whitening transformation of the dependent variable that must be estimated from the data. The asymptotic normality of the proposed estimators is established under mild conditions. We demonstrate, using both simulation and case studies, that the proposed estimators are more efficient than the traditional locally linearmethods which fail to account for ST correlation.
Spatially correlated data appear in many environmental studies, and consequently there is an increasing demand for estimation methods that take account of spatial correlation and thereby improve the accuracy of estima...
详细信息
Spatially correlated data appear in many environmental studies, and consequently there is an increasing demand for estimation methods that take account of spatial correlation and thereby improve the accuracy of estimation. In this paper we propose an iterative nonparametric procedure for modelling spatial data with general correlation structures. The asymptotic normality of the proposed estimators is established under mild conditions. We demonstrate, using both simulation and case studies, that the proposed estimators are more efficient than the traditional locally linearmethods which fail to account for spatial correlation. Firstly, we consider spatial correlation and spatial heterogeneity simultaneously. Secondly, we consider a general spatial correlation structure (second-order stationarity and isotropy) rather than assuming that the correlation satisfies some specific form (such as that given by a spatial autoregressive model). Finally we establish the asymptotic normality of our estimators under mild conditions. The results of our simulation and case studies indicate that our estimators perform better than those arising from traditional locally linearmethods which ignore spatial correlation.
Spatially correlated data are involved in various environmental studies, thus it is necessary to propose spatial estimation methods that capture spatial correlation so as to improve the accuracy of estimation. In this...
详细信息
Spatially correlated data are involved in various environmental studies, thus it is necessary to propose spatial estimation methods that capture spatial correlation so as to improve the accuracy of estimation. In this paper, we propose a three-steps estimation procedure for spatial models with spatial autoregressive error structure. The asymptotic normality of the estimator (m) over tilde*(x) shows that it is more efficient than traditional locallinear estimator (m) over cap (x), which ignores the spatial correlation. Results from a simulation study also show that m (m) over tilde*(x) has a better finite sample performance than (m) over cap (x).
暂无评论