# for, e.g., four random individuals
x.sub<-data[data$ID %in% sample(1:16, 4),]
On Tue, Jul 26, 2011 at 10:10 AM, Soanes, Louise
<Louise.Soanes at liverpool.ac.uk> wrote:> Hello
> I have been trying to figure out how to randomly select a number of
records. I have a column "ID" which contains 16 individuals (numbered
1-16), each individual has a few hundred rows of GPS locations associated with
it. I am trying to select a random sample of these individuals (with all their
associated GPS locations) to run a kernel density analysis on, and need to
repeat this several hundred times for each number of individuals in a sample.
>
> For example: I would like to be able to randomly select all the data
associated with 2 individuals (out of my 16) 100 times to run the analysis on
and then randomly select 3 individuals from my 16 individuals 100 times.... and
then randomly select 4 individuals 100 times ....and so on.
>
> At the moment I am using:
>
> data<-read.csv("All.csv")
> x.sub<-data[data$ID %in% c(10,8),]
>
> I have just been typing in random numbers to select individuals from my
total number of 16 for the subsampling which was ok when I just wanted 2
individuals from my 16 but as I include more individuals in my sample this is
becoming more painstaking! So does anybody know how I can write a command so
that R randomly selects a specified number of individuals from my ID column.
>
> If anybody can help I would really appreciate it
> Many thanks
> Louise Soanes
> University of Liverpool
>
>
--
Sarah Goslee
http://www.functionaldiversity.org