RMark Newbie, Phi Intercept >1, P Intercept Negative value

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

RMark Newbie, Phi Intercept >1, P Intercept Negative value

Postby JustinH » Tue Oct 24, 2017 9:22 pm

Hello all,

I am new to R and MARK and RMark. So my apologies if I should have been able to solve this on my own.

I have followed the steps of setting up my input file for RMark. It has been been made as a .txt file. My input code is:
Code: Select all
cjs<-read.table(file.choose(), colClasses =c("character", "character", "character","numeric","character","character"), sep="\t", header = TRUE)


When I run the default RMark CJS model:

Code: Select all
cjs.lt<-mark(cjs)


M results are:
Name : Phi(~1)p(~1)

Npar : 2
-2lnL: 9758.741
AICc : 9762.745

Beta
estimate se lcl ucl
Phi:(Intercept) 2.428614 0.0561113 2.318636 2.538592
p:(Intercept) -1.692503 0.0366246 -1.764288 -1.620719


Real Parameter Phi

1 2 3 4 5
1 0.9189834 0.9189834 0.9189834 0.9189834 0.9189834

...

Real Parameter p

2 3 4 5 6
1 0.1554469 0.1554469 0.1554469 0.1554469 0.1554469


I don't understand the Phi Intercept value can be greater than 1, and have a negative P value.

Could there be something wrong with my input data? I have tried to find similar issues without success.

Thank you!

Justin
JustinH
 
Posts: 2
Joined: Mon Oct 23, 2017 2:51 pm

Re: RMark Newbie, Phi Intercept >1, P Intercept Negative val

Postby cooch » Tue Oct 24, 2017 9:28 pm

Because you're looking at the beta estimates, which are derived on the logit scale. For them to 'make sense', you need to 'back-transform' from logit -> real.

All of this is described in detail in the MARK book. If you are a self-professed newbie, you really should read chapters 1 -> 7 of the book, carefully (your particular question is dealt with in chapter 6), before getting down and dirty with your data.

Said book is found here: http://www.phidot.org/software/mark/docs/book/
cooch
 
Posts: 1628
Joined: Thu May 15, 2003 4:11 pm
Location: Cornell University

Re: RMark Newbie, Phi Intercept >1, P Intercept Negative val

Postby JustinH » Wed Oct 25, 2017 12:40 pm

Thank you cooch, the help is much appreciated. I will work through those chapters!

Cheers,

Justin
JustinH
 
Posts: 2
Joined: Mon Oct 23, 2017 2:51 pm


Return to RMark

Who is online

Users browsing this forum: No registered users and 19 guests