Help with group interactions

questions concerning analysis/theory using program MARK

Help with group interactions

Postby ghol » Mon Dec 11, 2006 11:27 pm

Hello - I am a relative newcomer to MARK and am having trouble developing models to look at interactions between groups (factors). Here is a sample of my .inp file:

010000 1 0 0 0 1 1 0 1 0;
000111 1 0 1 0 0 1 0 1 0;
000111 1 0 0 0 1 1 0 1 0;
000100 1 0 1 0 0 1 0 1 0;
000110 1 0 1 0 0 1 0 1 0;
000111 1 0 0 1 0 1 0 1 0;

The 9 groups in the file represent females, males, juveniles, sub-adults, adults, control sites, treatment sites, poor habitat quality, and good habitat quality, respectively. As an example, how would I go about developing a model that looks at the interaction between sex and habitat quality? i.e. how do I produce survival estimates for females (and males) in both poor and good quality sites, so that comparisons between the two site types can be made?

Any advice would be most appreciated.

Regards
Greg.
ghol
 
Posts: 1
Joined: Sun Dec 10, 2006 8:03 pm

Postby abreton » Tue Dec 12, 2006 12:05 am

I think you have to start by modifying the group section of your encounter histories (e.g.):
EH
010000
Groups
F M J SA A C T P G
1 0 0 0 1 1 0 1 0;

The EH is fine, but the group section says you have 1 female with EH "010000", 1 adult with EH "010000", 1 control group with EH "010000" and 1 poor quality habitat with EH "010000". I suspect, that what you really wanted was 1 adult female from the control group and poor habitat with EH "010000". To get that, you need to redefine your groups:

1 0 0 0 0 0 0 0 0 = 1 adult female, control group, poor habitat

And now define your other groups:

0 1 0 0 0 0 0 0 0 = 1 adult female, control group, good habitat
0 0 1 0 0 0 0 0 0 = 1 juvenile female, control group, poor habitat
...etcetera until you run out of groups (if you run out of columns before you run out of groups, then you'll need to add more group columns).

Alternatively, you can write:
24 0 0 0 0 0 0 0 0 = 24 adult females, control group, poor habitat
Or,
24 15 0 0 0 0 0 0 0 = 24 adult females, control group, poor habitat and 15 adult females, control group, good habitat - all with EH 010000.

When you import your data into MARK, make sure you define each group carefully so you can recognize it (e.g., group1 = F SA C P) when you start manipulating the PIMs. The material I introduced here, and the models that you want to build are covered (though with fewer groups) in the first few chapters of "A Gentle Introduction to program MARK" (http://www.phidot.org/software/mark/docs/book/). I recommend Chapters 1-8, and also have a look at Chapter 12. Good luck - andre
abreton
 
Posts: 111
Joined: Tue Apr 25, 2006 8:18 pm
Location: Insight Database Design and Consulting


Return to analysis help

Who is online

Users browsing this forum: No registered users and 2 guests

cron