Model selection in PRESENCE

questions concerning analysis/theory using program PRESENCE

Model selection in PRESENCE

Postby mspinola » Thu Oct 23, 2008 11:48 am

Dear list members,

I fitted several occupancy models using Presence, but the first 2 models (the 1st has a weight of 0.88) have very low precision on the parameter estimates and some of the parameters were not estimated (the model have too many parameters). However the 3rd model has good estimates with reasonable precision. What should I do? Is it possible to discard the 2 first models based on the lack of precision and difficulty to estimate some parameters?
Is it appropriate to say: "I did not consider the first 2 models given their lack of precision on the parameter estimates"?
Thank you very much in advance.
Best,

Manuel
mspinola
 
Posts: 16
Joined: Tue Nov 06, 2007 11:24 am

Postby darryl » Thu Oct 23, 2008 11:43 pm

Hi Manuel
What do you mean "parameters were not estimate"? How much/what have you tried to resolve the estimation issues?
Darryl
darryl
 
Posts: 498
Joined: Thu Jun 12, 2003 3:04 pm
Location: Dunedin, New Zealand


Return to analysis help

Who is online

Users browsing this forum: No registered users and 4 guests