CJS model with year as covariate

Forum for discussion of general questions related to study design and/or analysis of existing data - software neutral.

CJS model with year as covariate

Postby Lutfor_Rahman » Thu Sep 13, 2012 12:49 pm

Dear Forum,
I have got weekly post-fledging monitoring data upto 4 weeks after fledging of chicks from nests.
Got this data in 5 different years such as year 2006-2011.
I would like to use CJS model with year as one of the coveriates. Can I use as 2006, 2007, 2008, 2009 , 2010..with my encounter histories data. I would like to see is there any yearly variation in survival?

I will appreciate your kind help.

Regards
Lutfor
UK
Lutfor_Rahman
 
Posts: 12
Joined: Thu Jul 07, 2011 7:32 am

Re: CJS model with year as covariate

Postby egc » Fri Sep 14, 2012 6:47 am

Lutfor_Rahman wrote:Dear Forum,
I have got weekly post-fledging monitoring data upto 4 weeks after fledging of chicks from nests.
Got this data in 5 different years such as year 2006-2011.
I would like to use CJS model with year as one of the coveriates. Can I use as 2006, 2007, 2008, 2009 , 2010..with my encounter histories data. I would like to see is there any yearly variation in survival?

I will appreciate your kind help.

Regards
Lutfor
UK


This has nothing to do with RMark (or MARK necessarily...), so I'm going to move this to the 'general questions' subforum.
egc
Site Admin
 
Posts: 201
Joined: Thu May 15, 2003 3:25 pm

Re: CJS model with year as covariate

Postby bacollier » Fri Sep 14, 2012 4:55 pm

Lutfor_Rahman wrote:Dear Forum,
I have got weekly post-fledging monitoring data upto 4 weeks after fledging of chicks from nests.
Got this data in 5 different years such as year 2006-2011.
I would like to use CJS model with year as one of the coveriates. Can I use as 2006, 2007, 2008, 2009 , 2010..with my encounter histories data. I would like to see is there any yearly variation in survival?

I will appreciate your kind help.

Regards
Lutfor
UK


Lutfor,

First, yes you can. Whether you should or not is another question as I suspect there is variation, its just how much magnitude you need to see for it to be deemed important.

Second, based on your question, you need to spend some time RTFM, especially cp 1-5, and maybe working through an example or two.

bret
bacollier
 
Posts: 230
Joined: Fri Nov 26, 2004 10:33 am
Location: Louisiana State University

Re: CJS model with year as covariate

Postby Lutfor_Rahman » Mon Sep 17, 2012 5:38 am

Dear Bret,

Thank you very much for your kind response.
Could you please elaborate what is "RTFM". Apologise for my limitation.
I have read book named" A gentle Introduction" bu Cooch and White and done their excercise.

Here I have provide samle example of my data and arranged them for analysis: If you kindly look at and advice me, would be great help also.

Weekly Encounter histories in first four weeks after fledging of brids
Covariates are:
1) Natural or Artificial site
2) Year
3) Brood size in a nest
4) Tag type used
5) Day of fledging

Questions: I am trying to find most persimonious model and also looking into is there any survival difference between natural and artificial site, and between years, tage types and how day of fledging (Day in the year) and brood size affect survival?

1111 1 0 2006 3 0 194;
1111 1 0 2006 3 0 194;
1111 1 1 2006 2 1 185;
1111 1 1 2006 3 1 192;
1111 1 0 2007 3 0 192;
1000 1 0 2007 4 0 192;
1100 1 0 2007 5 1 163;
1110 1 1 2008 5 1 163;
1111 1 1 2008 5 0 163;
1111 1 1 2008 5 0 163;
1110 1 0 2008 2 1 172;
1110 1 0 2008 2 0 172;
1111 1 1 2009 4 0 150;
1111 1 1 2009 4 0 150;


With thanks
Lutfor
UK
Lutfor_Rahman
 
Posts: 12
Joined: Thu Jul 07, 2011 7:32 am

Re: CJS model with year as covariate

Postby bacollier » Mon Sep 17, 2012 10:19 am

Lutfor_Rahman wrote:Dear Bret,

Thank you very much for your kind response.
Could you please elaborate what is "RTFM". Apologise for my limitation.
I have read book named" A gentle Introduction" bu Cooch and White and done their excercise.


RTFM means read the manual, specifically see section 4.2 and especially Chapter 6 for various ways of setting up what you are intending to do. You can lump all the data together into one analysis with various effects of group (e.g., your year variables) or various treatment effects you have listed like site, tag type, or you can use individual covariates such as brood size and day of fledgling. There are multiple examples of doing everything you want to do in the manual, as well as details on how to set it all up.

For instance, to help you along, you could adjust the DM very easily model effects of your individual covariates (Section 6.8 ) on survival using a structure something like:

1 DaysofFledging

dig a little deeper into your review of the manual, its all there,

bret
bacollier
 
Posts: 230
Joined: Fri Nov 26, 2004 10:33 am
Location: Louisiana State University

Re: CJS model with year as covariate

Postby Lutfor_Rahman » Thu Sep 20, 2012 4:40 am

Thank you so much Bret.
The manual you mentioned that is the manual "A Gentle Introduction" by Cooch and White? As I could not found any section with 6.8 on that book. Please let know if anyother manual available.

With regards
Lutfor
Lutfor_Rahman
 
Posts: 12
Joined: Thu Jul 07, 2011 7:32 am


Return to analysis & design questions

Who is online

Users browsing this forum: No registered users and 1 guest

cron