Bayesian delta normal spatio-temporal model for zero inflated biological data

The changes in the population density of a demersal species of the North-Western Ionian Sea over spatial and temporal scales and in response to anthropogenic and environmental factors is evaluated. Biological data were collected during trawl surveys carried out from 1995 to 2006 as part of the international project MEDITS (MEDiterranean International Trawl Surveys). The density (N/km2) index was computed for a number of hauls identified by time, depth, geographic coordinates and geographical sector. A bayesian delta normal model was estimated to evaluate the spatio-temporal changes in the density of a particular species of crustacean known as deep-water rose shrimp, Parapenaeus longirostris. Model estimation was implemented using the JAGS software, specifying the zero-inflated likelihood of the population density by the “zeros trick” method. The study highlights nonlinear spatial and temporal effects and the significant influence of the Winter North Atlantic Oscillations index on the deep-water rose shrimp density distribution.