Constrained, Covariance-Matching Constrained and Universal Point or Block Kriging

Provides functions for efficient computation of non-linear spatial predictions with local change of support (Hofer, C. and Papritz, A. (2011) "constrainedKriging: An R-package for customary, constrained and covariance-matching constrained point or block kriging" ). This package supplies functions for two-dimensional spatial interpolation by constrained (Cressie, N. (1993) "Aggregation in geostatistical problems" ), covariance-matching constrained (Aldworth, J. and Cressie, N. (2003) "Prediction of nonlinear spatial functionals" ) and universal (external drift) Kriging for points or blocks of any shape from data with a non-stationary mean function and an isotropic weakly stationary covariance function. The linear spatial interpolation methods, constrained and covariance-matching constrained Kriging, provide approximately unbiased prediction for non-linear target values under change of support. This package extends the range of tools for spatial predictions available in R and provides an alternative to conditional simulation for non-linear spatial prediction problems with local change of support.