Supplement 1. WinBUGS 1.4 code for hierarchical spatial N-mixture and occupancy models.

File List HierarchicalSpatialNmixtureModel.odc - WinBUGS 1.4 code.<br> HierarchicalSpatialOccupancyModel.odc - WinBUGS 1.4 code. Description The file HierarchicalSpatialNmixtureModel.odc contains WinBUGS code, simulated data, and initial values to run an example hierarchical spatial <i>N</i>-mixture model based on count data and modified from (Royle, J. A. 2004. <i>N</i>-mixture models for estimating population size from spatially replicated counts. Biometrics 60:108–115.). Spatial and non-spatial normal random effects are employed for both occupancy probability [which is related to the Poisson parameter lambda = -log(1- psi))] and capture probability. The model employs the hierarchical half-Cauchy prior for random effect standard deviations from Gelman [2006. Prior distributions for variance parameters in hierarchical models (Comment on article by Brown and Draper). Bayesian Analysis 3:515–534).]. The file HierarchicalSpatialOccupancyModel.odc contains WinBUGS code, simulated data, and initial values for a hierarchical spatial occupancy model. The code employs a sequential approach to modeling the binary detection data to avoid specifying a new sampling distribution which would be necessary to directly use the likelihood in MacKenzie et al. (2002, Estimating site occupancy rates when detection probabilities are less than 1. Ecology 83:2248–2255.). The hierarchical half-Cauchy prior for random effect standard deviations is also employed.