1

I have been using R for a little while now, and can usually search for answers to my questions. This time I am stumped. I am using R version 3.2.2 (2015-08-14) -- "Fire Safety" to analyze mark-recapture data. The code is located in package RCapture. We had four sampling occasions in which we captured and marked 48 individuals over a period of several months. Therefore, I wanted to run the data through an open population model. the p* notation is the sampling period, 0 and 1 were absent and present at that sampling period, and the frequency is how many were caught in that pattern (again, not sure how much depth is needed here). 

p1 p2 p3   p4   freq
0   0   0   1   1
0   0   1   0   9
0   0   1   1   0
0   1   0   0   10
0   1   0   1   0
0   1   1   0   7
0   1   1   1   3
1   0   0   0   13
1   0   0   1   0
1   0   1   0   0
1   0   1   1   0
1   1   0   0   5
1   1   0   1   0
1   1   1   0   1
1   1   1   1   0

The output of str(terp):

data.frame': 15 obs. of 5 variables: 
 $ p1 : int 0 0 0 0 0 0 0 1 1 1 ... 
 $ p2 : int 0 0 0 1 1 1 1 0 0 0 ... 
 $ p3 : int 0 1 1 0 0 1 1 0 0 1 ... 
 $ p4 : int 1 0 1 0 1 0 1 0 1 0 ... 
 $ freq: int 1 9 0 10 0 7 3 13 0 0 ...

The code used was as follows:

op1=openp(terp, dfreq=TRUE)

The code ran fine, but I am trying to figure out why the output looks as it does. Normally, the output will give an estimate of the abundance with a standard error estimate, but the output I received gives an estimate with a 0 standard error, i.e. estimate = 26, standard error = 0. 

           estimate  stderr
period 1        --      --
period 2        26       0
period 3        20       0
period 4        --      --

The final estimate of total population just seems to be the total number captured:

Total number of units who ever inhabited the survey area:
              estimate  stderr
all periods        49       0

Total number of captured units: 49

The capture probabilities have the same issue as the abundances, they are an estimate of 1 with no standard error. I am not sure if this is the right outlet, but I have looked all over for reasons this might be occurring. I wanted to verify the code is correct, and could this just be low sample size affecting the output?

Ben Bolker
  • 211,554
  • 25
  • 370
  • 453
Ed McG
  • 11
  • 2
  • Unless an expert in this area happens to come along you may be hard pressed to get an answer, as (outside of ecology) this is a somewhat niche question. Suggestions: (1) include *all* of the data, or at least enough to provide us with a [reproducible example](http://stackoverflow.com/questions/5963269/how-to-make-a-great-r-reproducible-example) [follow link for advice on data presentation]. (2) you might want to show us `str(terp)`. (3) if you don't get useful advice here, you might try on r-sig-ecology@r-project.org – Ben Bolker Sep 14 '16 at 13:34
  • 'data.frame': 15 obs. of 5 variables: $ p1 : int 0 0 0 0 0 0 0 1 1 1 ... $ p2 : int 0 0 0 1 1 1 1 0 0 0 ... $ p3 : int 0 1 1 0 0 1 1 0 0 1 ... $ p4 : int 1 0 1 0 1 0 1 0 1 0 ... $ freq: int 1 9 0 10 0 7 3 13 0 0 ... Ben, I was afraid of that. I should have edited the post to say that the data shown is all of the raw data. I tried to post to r-sig, but it got rejected with no explanation, I will definitely try again. Here was the output from str(terp). I am sorry, I cannot figure out the formatting in the comments section to insert the code – Ed McG Sep 14 '16 at 13:46

0 Answers0