J. E. Hines, J. D. Nichols, J. A. Royle, D. I. MacKenzie, A. M. Gopalaswamy, N. Samba Kumar, and K. U. Karanth. 2010. Tigers on trails: occupancy modeling for cluster sampling. Ecological Applications 20:1456–1466.

Supplement

WinBUGS code for model .
Ecological Archives A020-053-S1.

Copyright

Authors
File list (downloads)
Description

Author(s)

James E. Hines
USGS
Patuxent Wildlife Research Center
12100 Beech Forest Rd
Laurel, Md. 20708 USA
email:jhines@usgs.gov

James D. Nichols
USGS
Patuxent Wildlife Research Center
12100 Beech Forest Rd
Laurel, Md. 20708 USA
email:jnichols@usgs.gov

J. Andrew Royle
USGS
Patuxent Wildlife Research Center
12100 Beech Forest Rd
Laurel, Md. 20708 USA
email:aroyle@usgs.gov

Darryl MacKenzie
Proteus Research & Consulting Ltd.
PO Box 5193
Dunedin, New Zealand
email:darryl@proteus.co.nz

A. M. Gopalaswamy
Wildlife Conservation Society - India Program
Centre for Wildlife Studies
1669, 31st Cross, 16th Main
Banashankari 2nd Stage
Bengaluru - 560070
email:arjungswamy@gmail.com

N. Samba Kumar
Wildlife Conservation Society - India Program and Centre for Wildlife Studies
1669, 31st Cross, 16th Main, Banashankari 2nd Stage
Bengaluru - 560 070, India
email:samba.wcs@gmail.com

K.U. Karanth
Centre for Wildlife Studies
403, Seebo Apartments
26-2, Aga Abbas Ali Road
Bangalore-560042
INDIA
email:ukaranth@gmail.com

File list

spatial_dep_model.txt -- WinBugs model definition file
spatial_dep_script.txt -- WinBugs script file
spatial_dep_data.txt -- Sample data file

Description

Input data consists of the matrix h_ij, the detection/nondetectin data for site i, survey j.

In the code, z_i denotes presence (z_i =1) or absence (z_i=0) at the level of the sample unit, i; y_ij denotes local presence (y_ij = 1) or absence (y_ij = 0) on segment j; and h_ij denotes detection (h_ij =1) or not (h_ij =0) on segment j of sample unit i. Each of these random variables is modeled as a Bernoulli trial, the latter two conditional on occupancy at sample unit and segment scale:

All model parameters were given uniform prior distributions, U(0,1).