J. Heikkinen et E. Arjas, NONPARAMETRIC BAYESIAN-ESTIMATION OF A SPATIAL POISSON INTENSITY, Scandinavian journal of statistics, 25(3), 1998, pp. 435-450
A method introduced by Arjas & Gasbarra (1994) and later modified by A
rjas & Heikkinen (1997) for the non-parametric Bayesian estimation of
an intensity on the real line is generalized to cover spatial processe
s. The method is based on a model approximation where the approximatin
g intensities have the structure of a piecewise constant function. Ran
dom step functions on the plane are generated using Voronoi tessellati
ons of random point patterns, Smoothing between nearby intensity value
s is applied by means of a Markov random field prior in the spirit of
Bayesian image analysis. The performance of the method is illustrated
in examples with both real and simulated data.