Intensity Estimation for Spatial Point Processes Observed with Noise

This article introduces a kernel estimator of the intensity function of spatial point processes taking into account location errors. The asymptotic properties of the estimator are derived and a bandwidth selection procedure is described. A simulation study compares our results with that of the classical kernel estimator and shows that the edge-corrected deconvoluting kernel estimator is more appropriate. Copyright (c) Board of the Foundation of the Scandinavian Journal of Statistics 2008.