Careful Prior Specification Avoids Incautious Inference for Log-Gaussian Cox Point Processes. Issue 3 (2nd November 2018)

• Record Type: Journal Article
• Authors: S⊘rbye, Sigrunn H.; Illian, Janine B.; Simpson, Daniel P.; Burslem, David; Rue, Håvard
• Is Part Of: Journal of the Royal Statistical Society. Volume 68:Issue 3(2019)
• Page Start: 543
• Page End: 564
• Publication Date: 2018-11-02
• Subjects: Bayesian analysis -- Penalized complexity prior -- R-INLA -- Spatial modelling -- Spatial point process; Statistics -- Periodicals; 519.5
• DOI: 10.1111/rssc.12321
• Languages: English
• ISSNs: 0035-9254

Abstract

Summary: Hyperprior specifications for random fields in spatial point process modelling can have a major influence on the results. In fitting log-Gaussian Cox processes to rainforest tree species, we consider a reparameterized model combining a spatially structured and an unstructured random field into a single component. This component has one hyperparameter accounting for marginal variance, whereas an additional hyperparameter governs the fraction of the variance that is explained by the spatially structured effect. This facilitates interpretation of the hyperparameters, and significance of covariates is studied for a range of hyperprior specifications. Appropriate scaling makes the analysis invariant to grid resolution.