Page 1 of 1

Robust design and estimating abundances

PostPosted: Sat Sep 12, 2020 3:15 pm
by jln1234
Hello all,
Sorry for the most likely basic question but I am a bit confused about how to get abundance estimates with a robust design. In a gentle introduction, page 15-13, it states that if temporary immigration does not occur than abundance can be estimated for all time periods. It then refers to JS method in Kendall and Pollock 1992. What I am trying to figure out is how to set this up with rmark. A little information about my data is I am comparing 3 sites that had a different habitat modification applied to it and I am looking at the change in survival, capture rates, and hopefully abundance of the small mammals over time.

Code: Select all
time.intervals=c(0,0,1,0,0,1,0,0,1,0,0,1,0,0,1,0,0)
S.time=list(formula=~time*species*grid)
p.time.session=list(formula=~-1+session:time,share=TRUE)
GammaDoublePrime.random=list(formula=~time,share=TRUE)
model.2=mark(data = rob, model = "Robust",
             time.intervals=time.intervals,
             model.parameters=list(S=S.time,
                                   GammaDoublePrime=GammaDoublePrime.random,p=p.time.session),threads=2)

This is an example of what I have be doing in R, it is heavily based of the ?robust help example. The grids are the different sites with different habitat modification and species is well the different small mammal species. I know this is not even close to the model that I want to run but how do I modify so I can also start estimating abundance? thank you in advance for your help.

Re: Robust design and estimating abundances

PostPosted: Mon Sep 14, 2020 2:27 pm
by jlaake
You get abundance estimates in model$results$derived if the fitted object is named model. Beyond that I'm not sure what you mean. If you need to fix real parameters like the gamma's see the fixed post on the forum (at the top) about fixing real parameters. Also described in workshop notes.

Re: Robust design and estimating abundances

PostPosted: Mon Sep 14, 2020 11:15 pm
by Bill Kendall
I'm glad Jeff answered your question, with respect to the mechanics of getting it out of RMark. Just a comment about your citation of the RD chapter of the Gentle Introduction. You don't need that assumption about temporary emigration in order for all the individual abundances to be estimable. That restriction applied to estimating survival and recruitment (or lambda for that matter) for all periods.