hello BUGS users,
I had a number of helpful responses to my question about getting a
mark-recapture analysis to run (I include the original request below).
Olivier Gimenez doctored the code succesfully, a happy solution since
I'd used code of his as a starting point (before proceeding to corrupt
it)! He used the trick of constraining the final multinomial probability
of a row to equal 1-the sum of the rest.
Dan Rawding pointed out that this model could be run using a different
format of data, as spelt out in paper by Brooks (2000).
A number of people pointed out that the last values for phi (survival)
and p (capture) in the series are confounded, ie there is no information
in the data to distinguish whether absence on the last occasion is due
to (i) mortailty or (ii) non-capture. My original sepcification made no
allowance for this constraint and I suspect this is where the problem
lay, but Olivier Gimenez saved me the trouble of another night trying to
figure it out by sending me the modified code.
thanks again to all those who replied.
Neil
hello fellow BUGS users/misusers,
I'm running a mark-recapture analysis on some wildlife data. For this
purpose I used and modified code used by Gimenez et al for what I want
to do is similar in the first instance.
I am looking to estimate survival (phi) and capture (p) probabilities
and I want these to be year-specific (as oppposed to constant). If I run
the model using constant phi and p, model runs ok. If I then run model
allowing for year-specific phi, again model runs ok. However, if I
include in addition, year-specific values for p, the model fails and I
get the message "elements of proportion vector of multinomial y[1,1]
must sum to unity".
"y" is the label for my data.
I've tried various strategies, but without success. If anyone has
experience with this kind of analysis (or if not!) and can advise, I'd
be most grateful. Can send code and data on request.
regards,
Neil
--
----------------------------------------------------------------------
Neil Walker, MSc Phone: +44 (0)1453 861417
Biostatistician GTN: 5129
Wildlife Disease Ecology Team Fax: +44 (0)1453 860132
Food & Environment Research Agency (Fera)
Woodchester Park
Nympsfield
Gloucs. GL10 3UJ Web: http://www.csl.gov.uk
----------------------------------------------------------------------
----------------------------------------------------------------------
Visit our website at www.badgerecology.org
-------------------------------------------------------------------
This list is for discussion of modelling issues and the BUGS software.
For help with crashes and error messages, first mail [log in to unmask]
To mail the BUGS list, mail to [log in to unmask]
Before mailing, please check the archive at www.jiscmail.ac.uk/lists/bugs.html
Please do not mail attachments to the list.
To leave the BUGS list, send LEAVE BUGS to [log in to unmask]
If this fails, mail [log in to unmask], NOT the whole list
|