Time varying individual covariates

questions concerning analysis/theory using program MARK

Time varying individual covariates

Postby Mardagosa » Sat Sep 18, 2021 1:47 pm

I have two questions regarding individual covariates. I tried exporting data to MARK to test for goodness fit. However, the median chat doesn't seem to work with individual covariates (as the pop up window suggested). Is there another way to do this?
Second, I want to build a database that has multiple years and size changes as an individual covariate. How should the database be constructed as in some years I do not have data for some individuals?
Thanks
Mardagosa
 
Posts: 10
Joined: Wed Sep 08, 2021 10:28 am

Re: Time varying individual covariates

Postby cooch » Sat Sep 18, 2021 4:25 pm

Doesn't sound like you've read Chapter 11 in the MARK book. Both subjects you ask about are covered (section 11.6, and 11.9). Be advised there is no perfect solution to missing time-varying individual covariates, but depending on what proportion of your encounters are 'missing', there are things you can try.
cooch
 
Posts: 1628
Joined: Thu May 15, 2003 4:11 pm
Location: Cornell University

Re: Time varying individual covariates

Postby sbonner » Sun Sep 19, 2021 8:26 am

Hi Mardagosa,

Evan is completely correct that fitting models with time-varying individual covariates is limited in MARK, though there are some options outside of MARK.

If your experiment included recoveries of dead animals as well as the capture of live animals then you can fit the trinomial model of Catchpole, Morgan, and Tavecchia (2008)(https://rss.onlinelibrary.wiley.com/doi/abs/10.1111/j.1467-9868.2007.00644.x). Instructions are provided in Bonner (2012) (https://besjournals.onlinelibrary.wiley.com/doi/10.1111/j.2041-210X.2012.00265.x).

If your experiment did not include dead recoveries then you can still fit this model by setting the recovery probability equal to 0. I call this the binomial model. There are some disadvantages to this model about which I have a manuscript in preparation, but you can do it.

Alternatively, if you are comfortable working outside of MARK then there are alternative methods I'd be happy to chat about this off the list and can provide further help if you want to send me an e-mail: simon.bonner@uwo.ca.

Cheers!
sbonner
 
Posts: 71
Joined: Mon Aug 15, 2005 7:38 pm
Location: University of Western Ontario, Canada


Return to analysis help

Who is online

Users browsing this forum: No registered users and 10 guests