Supervised classification of the observation of spatial Gaussian process with known covariance function

Abstract

The problem of classification of spatial Gaussian process observation into one of two populations specified by different regression mean models and common known covariance function is considered. ML estimators of regression parameters are plugged in the Bayes discriminant function. The asymptotic expansion of the expected error rate associated with Bayes plug – in discriminant function is derived. Numerical analysis of the accuracy of the approximation of the expected error rate based on derived asymptotic expansion in the small training sample case is carried out. This approximation is proposed as optimality criterion function for spatial sampling design.