MPS-RR 2001-25
August 2001

Statistical inference for transformation inhomogeneous point processes

Eva B. Vedel Jensen

Linda Stougaard Nielsen

Abstract

Statistical inference for exponential inhomogeneous Markov point processes by transformation is discussed. It is argued that the inhomogeneity parameter can be estimated, using a partial likelihood based on an inhomogeneous Poisson point process. The inhomogeneity parameter can thereby be estimated without taking the interaction into account, which simplifies the statistical analysis considerably. Furthermore, an easily computable test for homogeneity is presented. Analysis of two data sets and simulation experiments support the results.

Availability: [ gzipped ps-file ] [ pdf-file ]

[ Help on down-loading/viewing/printing ]