Supplement 1. R and BUGS code to fit all the models presented.

File List
BUGS-Models.bug (MD5: bbc0c6df0dc6e68ff25a3172ad349f07)

FormatData_forBUGS.r (MD5: cb618b5c9dae1c6a5c19730541f8a74a)

Likelihoods.r (MD5: 0e56760d67549e4e6efc587d94097907)

SimulateData_Calibration.r (MD5: cf2a083f6a73bdb71db9d6c4966d8976)

SimulateData_ObservationConf.r (MD5: a08687fcc8a826dbebb64b7e57647b78)

SimulateData_SiteConf-MM.r (MD5: 885ee8cb22dea9bee08ea53d7cacaede)

SimulateData_SiteConf-MS.r (MD5: f826d94e8c110481c544696e94d5cf60 )

Description
The Four files named as SimulateData_xxx.r are used to simulate data for each of the four corresponding study design described in the text. Note that the site confirmation design has two variants: (1) the Multiple-Method design (MM) and (2) the Multiple-State design (MS). The file Likelihoods.r contains the likelihoods for the four models, and it can be run in R, as is. To run the Bayesian models in OpenBUGS (or WinBUGS), run the script FormatData_forBUGS first. It will transform the simulated data in the appropriate from for BUGS. Then, you can use the code in BUGS-Models.bug to run each of the four models presented in the paper.