R help - Mar 2011 - Fw: random sampling steps in R with replacement

Please note is with replacement



From: taby gathoni <tabieg@yahoo.com>
To: R help <r-help@r-project.org>
Sent: Thursday, March 10, 2011 11:53 AM
Subject: [R] random sampling steps in R

Dear all,

Could someone assist me in random sampling steps/code in R? I have a main sample
of  42 males and 165 females and I want to come up with about 1000 samples of 20
males and 20 females from this main sample. While at it, i would also like to
come up Accuracy  Ratios (ARs) with corresponding confidence intervals.

Please assist.


Thanks so much,

Taby


      
    [[alternative HTML version deleted]]

______________________________________________
R-help@r-project.org mailing list
https://stat.ethz.ch/mailman/listinfo/r-help
PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
and provide commented, minimal, self-contained, reproducible code.


      
	[[alternative HTML version deleted]]

Hello, Taby,

for your (first) problem take a look at

?sample

and its argument replace.


Regards -- Gerrit


On Thu, 10 Mar 2011, taby gathoni wrote:
> Please note is with replacement
>
>
> From: taby gathoni <tabieg at yahoo.com>
> To: R help <r-help at r-project.org>
> Sent: Thursday, March 10, 2011 11:53 AM
> Subject: [R] random sampling steps in R
>
> Dear all,
>
> Could someone assist me in random sampling steps/code in R? I have a 
> main sample of 42 males and 165 females and I want to come up with about 
> 1000 samples of 20 males and 20 females from this main sample. While at 
> it, i would also like to come up Accuracy Ratios (ARs) with 
> corresponding confidence intervals.
>
> Please assist.
>
>
> Thanks so much,
>
> Taby
>
>
>
>    [[alternative HTML version deleted]]
>
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.

Hi Taby,

this is not best solution for sure but it will give you, maybe, some ideas
:)
I am also looking forward to see other solutions.

data<-data.frame(id=1:(165+42),x=rep(c("male","female"),c(42,165)))
f<-function(x) {
str.sample<-list()
for (i in 1:length(levels(x$x)))
{
str.sample[[i]]<-x[x$x==levels(x$x)[i]
,][sample(tapply(x$x,x$x,length)[i],20,rep=T),]
}
strat.sample<-do.call("rbind",str.sample)
return(strat.sample)
}
f(data)
repl<-list()
for(i in 1:1000)
{
repl[[i]]<-f(data)
}
repl

Andrija

On Thu, Mar 10, 2011 at 10:04 AM, taby gathoni <tabieg@yahoo.com> wrote:
> Please note is with replacement
>
>
>
> From: taby gathoni <tabieg@yahoo.com>
> To: R help <r-help@r-project.org>
> Sent: Thursday, March 10, 2011 11:53 AM
> Subject: [R] random sampling steps in R
>
> Dear all,
>
> Could someone assist me in random sampling steps/code in R? I have a main
> sample  of  42 males and 165 females and I want to come up with about 1000
> samples of 20 males and 20 females from this main sample. While at it, i
> would also like to come up Accuracy  Ratios (ARs) with corresponding
> confidence intervals.
>
> Please assist.
>
>
> Thanks so much,
>
> Taby
>
>
>
>    [[alternative HTML version deleted]]
>
> ______________________________________________
> R-help@r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
>
http://www.R-project.org/posting-guide.html<http://www.r-project.org/posting-guide.html>
> and provide commented, minimal, self-contained, reproducible code.
>
>
>
>        [[alternative HTML version deleted]]
>
> ______________________________________________
> R-help@r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
>
http://www.R-project.org/posting-guide.html<http://www.r-project.org/posting-guide.html>
> and provide commented, minimal, self-contained, reproducible code.
>
	[[alternative HTML version deleted]]

Hi:

To get the samples, here's one approach:

df <- data.frame(gender = rep(c('F', 'M'), c(165, 42)), y =
rpois(207, 20))
# Sampling function to take 20 F and 20 M with replacement
# The sample function operates on the rows of df to get idx and then takes
# the y's corresponding to those rows
sfun <- function(x) {
    idx <- c(sample(1:165, 20, replace = TRUE), sample(166:207, 20, replace
= TRUE))
    x[idx]
   }

# Replicate the process 1000 times
u <- t(replicate(1000, sfun(df$y)))
> dim(u)
[1] 1000   40

The first 20 rows are F, the second 20 M.

HTH,
Dennis

On Thu, Mar 10, 2011 at 1:04 AM, taby gathoni <tabieg@yahoo.com> wrote:
> Please note is with replacement
>
>
>
> From: taby gathoni <tabieg@yahoo.com>
> To: R help <r-help@r-project.org>
> Sent: Thursday, March 10, 2011 11:53 AM
> Subject: [R] random sampling steps in R
>
> Dear all,
>
> Could someone assist me in random sampling steps/code in R? I have a main
> sample  of  42 males and 165 females and I want to come up with about 1000
> samples of 20 males and 20 females from this main sample. While at it, i
> would also like to come up Accuracy  Ratios (ARs) with corresponding
> confidence intervals.
>
> Please assist.
>
>
> Thanks so much,
>
> Taby
>
>
>
>    [[alternative HTML version deleted]]
>
> ______________________________________________
> R-help@r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>
>
>
>        [[alternative HTML version deleted]]
>
> ______________________________________________
> R-help@r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
>
	[[alternative HTML version deleted]]