Hello,
I'm interested in exploring parameter identifiability issues that arise in a multi-state occupancy model with an unobservable state. Unfortunately, I also have sparseness in the form of missing data (i.e., not all sites were visited in all years). Is it possible to accommodate missing data in E-SURGE, and if so, what format should the missing data take?
I know from reading the forum that U-CARE does not accommodate missing data in the MARK format, but that by fixing parameters it is possible to obtain unbiased estimates. However, in my occupancy scenario, the missing data do not occur consistently across sites, visits, and years so fixing parameters is not an option.
Thanks for any help you can provide.
Brittany
Ph.D. Candidate
Department of Fish, Wildlife, and Conservation Biology
Colorado State University
brittany.mosher@colostate.edu