A combined estimating function approach for fitting stationary point process models

Abstract

A composite likelihood technique based on pairwise contributions provides a computationally simple but potentially inefficient approach for fitting spatial point process models. We propose a new estimation procedure that improves the efficiency. Our approach combines estimating functions derived from pairwise composite likelihood estimation and estimating functions that account for correlations among the pairwise contributions. Our method can be used to fit a variety of parametric spatial point process models and can yield more efficient estimators for the clustering parameters than pairwise composite likelihood estimation. We demonstrate the efficacy of our proposed method through a simulation study and an application to the longleaf pine data.