Trouble estimating Pi

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

Trouble estimating Pi

Postby jctroxler » Sun Oct 28, 2012 3:35 pm

I am trying to run a Huggins full heterogeneity model. I have 8 occasions in my capture history, 2 mixtures, and a sex column, (81 individuals).

Note: only 2 parameters counted of 3 specified parameters
AICc and parameter count have been adjusted upward

Output summary for HugFullHet model
Name : pi(~1)p(~1)c(~1)

Npar : 3 (unadjusted=2)
-2lnL: 749.5595
AICc : 755.5967 (unadjusted=753.57809)

Beta
estimate se lcl ucl
pi:(Intercept) -0.1000000 799.1222400 -1566.379600 1566.1796000
p:(Intercept) -1.5088851 0.2850582 -2.067599 -0.9501711
c:(Intercept) -0.9745597 0.1173609 -1.204587 -0.7445323


Real Parameter pi
Group:sexFemale

0.4750208

Group:sexMale

0.4750208

p is 0.811 for both mixtures and both sexes. c is 0.273 for both mixtures and sexes. Any ideas what is going on with Pi?
Thanks
jctroxler
 
Posts: 5
Joined: Wed Oct 10, 2012 3:37 pm

Re: Trouble estimating Pi

Postby jlaake » Mon Oct 29, 2012 9:21 am

This question isn't really specific to RMark. You may want to try different starting values but also there may be insufficient information in your data to estimate both p,c and pi. You could try only estimating p and pi as an alternative to p and c model. You should think about what models make the most sense for your animal/sampling.

--jeff
jlaake
 
Posts: 1479
Joined: Fri May 12, 2006 12:50 pm
Location: Escondido, CA


Return to RMark

Who is online

Users browsing this forum: No registered users and 1 guest