A Poisson model for overdispersed spatial counts with misreporting

We propose a Poisson model for zero-inflated spatial counts contaminated by measurement error.We accommodate the excess of zeroes in the counts, consider the possible under/over reporting of the response and account for the neighboring structure of spatial areal units. Bayesian inferences are provided by MCMC implementation through the R package NIMBLE. The modeling approach is proposed to investigate the relation between the counts of wildfire occurrences in municipal areas and several potential socio-economic and environmental-driven factors, considering two neighboring regions in southern Italy (Apulia and Basilicata). Multiple sources of data with different spatial support are used and data were pre-processed in order to re-conduct the analysis to the municipal units. Results suggest the appropriateness of the approach and provide some insights on the features of wildfire occurrences.