Problems running Random Effects models

[Diego.Pavon]

Hi all,

I am currently trying to run random effects models in MARK and I am having several problems.
First, I have capture-recapture data on Ural owl (data since 1986 to 2010, 24 years). I want to assess the effect of changes in food abundance, climate(snow depth), forestry activity and population density on survival.
I have been following the Appendix D which deals with Random Effects, but I got very weird results.
I have specified the Intercept Only model and I have been presented the txt file with the estimates ( S-hat SE(S-hat) S-tilde SE(S-tilde) RMSE(S-tilde)). But, when I try to fit the model to the data i find that:

First, the SIN option is not activated. That is ok, I am using Logit. Second, when I click RUN, I get the normal window asking me to append the model to the browser, but there I can see a warning message that says: Error number 2 from VA09AD optimization routine.

Then I add the models to the browser, it looks like this:

Best model: phi(V+Sn)p(t) AIC = 2187.1491.... npar = 26
Random Effect: phi(V+Sn)p(t) intercept only .... deltaAIC = 307234.3484....npar=46.087

I would appreciate any help with this. Thank you very much in advance!

Diego

[cooch]

Hi all,

I am currently trying to run random effects models in MARK and I am having several problems.
First, I have capture-recapture data on Ural owl (data since 1986 to 2010, 24 years). I want to assess the effect of changes in food abundance, climate(snow depth), forestry activity and population density on survival.
I have been following the Appendix D which deals with Random Effects, but I got very weird results.
I have specified the Intercept Only model and I have been presented the txt file with the estimates ( S-hat SE(S-hat) S-tilde SE(S-tilde) RMSE(S-tilde)). But, when I try to fit the model to the data i find that:

First, the SIN option is not activated. That is ok, I am using Logit. Second, when I click RUN, I get the normal window asking me to append the model to the browser, but there I can see a warning message that says: Error number 2 from VA09AD optimization routine.

Then I add the models to the browser, it looks like this:

Best model: phi(V+Sn)p(t) AIC = 2187.1491.... npar = 26
Random Effect: phi(V+Sn)p(t) intercept only .... deltaAIC = 307234.3484....npar=46.087

I would appreciate any help with this. Thank you very much in advance!

Diego

Try giving it better (different) starting values, or use simulated annealing.