Stein hypothesis and screening effect for covariances with compact support (Q2192310)

The authors consider optimal unbiased linear prediction (kriging) which is widely used in spatial statistics to interpolate point observations of a mean-square continuous random field. The notion of ``screening effect'' is used to describe a situation where the interpolant depends mostly on those observations that are located nearest to the predictand. The phenomenon allows reducing considerably the computational burden associated with the kriging predictor when handling large data sets. The Matérn covariance function is considered as a good covariance function to yield screening effect but it is often recommended not to use covariance functions with a compact support. The authors show that some classes of covariance functions being compactly supported allow for a screening effect, in both regular and irregular settings of the spatial design. Further, numerical experiments suggest that the screening effect under a class of compactly supported covariance functions is even stronger than the screening effect under a Matérn model.