individual time-varying covariates

posts related to the RMark library, which may not be of general interest to users of 'classic' MARK

individual time-varying covariates

Postby ap123WY » Tue May 30, 2023 3:31 pm

Hello,

I am a student new to RMark and was curious 1) how and 2) where to incorporate capture effort into my analysis. Specifically, I am looking at long-term CMR data of birds and want to know how net hours and in which season sampling occurred impact survival and recruitment. I am using the "PradLambaMix" and "PradelRecMix" models. Since these aren't design covariates, I know I shouldn't add them directly to the design matrix.

I assume my net hours and season will be individual time-varying covariates, since, for each capture of an individual, the net hours and season (for whatever period we sampled in and caught that individual) will be unique. I want to include these as covariates in my capture probability model (something like cpmod = list(formula= ~nethours + season)- but first need to be able to match them to the individual ID, and then go from there. This is where I am stuck, so any input would be appreciated!

Thanks.
ap123WY
 
Posts: 1
Joined: Wed May 24, 2023 11:33 pm

Re: individual time-varying covariates

Postby jlaake » Wed May 31, 2023 9:44 pm

I have never used Pradel models before but I think they are a form of a Jolly Saber type of analysis which means that the initial capture probability is estimated. If that is true then I don't see how you can assign a net hours value for initial capture because it is only known after capture. The workshop notes for RMark describe how to define and use time varying individual covariates but you need to think about this more. You may be able to define areas as strata and then could assign a stratum specific net hours. Not sure.
jlaake
 
Posts: 1417
Joined: Fri May 12, 2006 12:50 pm
Location: Escondido, CA


Return to RMark

Who is online

Users browsing this forum: Google [Bot] and 14 guests

cron