Tigers on trails: occupancy modeling for cluster sampling

• DOI: 10.1890/09-0321.1
• Publication Date: 2010-06-22T21:35:54Z
• Authors: J. E. Hines; J. D. Nichols; J. A. Royle; D. I. MacKenzie; A. M. Gopalaswamy; N. Samba Kumar; K. U. Karanth
• Keywords: Occupancy; Statistical Inference

Occupancy modeling focuses on inference about the distribution of organisms over space, using temporal or spatial replication to allow detection process. Inference based strictly requires that replicates be selected randomly and with replacement, but importance these design requirements is not well understood. This paper an increasingly popular sampling are expected exhibit Markovian dependence. We develop two new occupancy models for data collected under this sort design, one underlying Markov model dependence other a trap response detections. then simulated fit standard models. Bias estimates was substantial models, smaller model, negligible process model. also from large‐scale tiger survey recently conducted in Karnataka State, southwestern India. In addition providing evidence positive relationship between habitat, selection statistics strongly supported use provides another tool decomposition process, which sometimes needed proper estimation may permit interesting biological inferences. designs employing replication, we note likely existence many replication. The developed here will useful either directly, minor extensions, as well. believe represent important additions suite tools now available conservation monitoring. More generally, work represents contribution topic cluster situations there need specific (e.g., reflecting dependence) variable(s) interest among subunits.