Inference for inhomogeneous clustered point processes

Description

Statistical inference is considered for a certain class of inhomogeneous Neyman-Scott processes depending on spatial covariates. Regression parameters obtained from a simple estimating function are shown to be asymptotically normal when the "mother" intensity for the Neyman-Scott process tends to infinity. Clustering parameter estimates are obtained using minimum contrast estimation based on the k-function. We apply the methodology to study how the intensity of tropical rain forest trees depends on topographical covariates.
StatusFinished
Effective start/end date01/08/200531/12/2007

Funding

  • <ingen navn>

Fingerprint

Point Process
Covariates
Estimating Function
Statistical Inference
Regression
Infinity
Clustering
Tend
Methodology
Estimate
Class