R help - Jul 2010 - choosing a random sample by precentage

hi all

i have found the follwoing way to choose a random sample by sample size (200):

ten_per_T2000 <- F_T2000_All[sample(nrow(F_T2000_All), 200), ]


 but i wondered if there is a way to choose a sample size by
precentage (10% etc..)

thx

ethan

Hi Ethan,

Sure with a bit of extra work:

x <- matrix(1:109, ncol = 1)
x[sample(nrow(x), trunc(nrow(x)*.1)), ]

you could also use round() in place of trunc(), you just need
something to get it to an integer.  If you didn't like having to type
the name several times you could make a simple function to do it for
you.

HTH,

Josh

On Thu, Jul 22, 2010 at 3:49 PM, Xebar Saram <zeltakc at gmail.com>
wrote:
> hi all
>
> i have found the follwoing way to choose a random sample by sample size
(200):
>
> ten_per_T2000 <- F_T2000_All[sample(nrow(F_T2000_All), 200), ]
>
>
> ?but i wondered if there is a way to choose a sample size by
> precentage (10% etc..)
>
> thx
>
> ethan
>
> ______________________________________________
> 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.
>


-- 
Joshua Wiley
Ph.D. Student, Health Psychology
University of California, Los Angeles
http://www.joshuawiley.com/

> -----Original Message-----
> From: r-help-bounces at r-project.org [mailto:r-help-bounces at r-
> project.org] On Behalf Of Xebar Saram
> Sent: Thursday, July 22, 2010 3:50 PM
> To: r-help at r-project.org
> Subject: [R] choosing a random sample by precentage
> 
> hi all
> 
> i have found the follwoing way to choose a random sample by sample size
> (200):
> 
> ten_per_T2000 <- F_T2000_All[sample(nrow(F_T2000_All), 200), ]
> 
> 
>  but i wondered if there is a way to choose a sample size by
> precentage (10% etc..)
> 
> thx
> 
> ethan
> 

Maybe something like:
>ten_per_T2000 <- F_T2000_All[sample(nrow(F_T2000_All),
0.1*nrow(F_T2000_All)), ]

Hope this is helpful,

Dan

Daniel J. Nordlund
Washington State Department of Social and Health Services
Planning, Performance, and Accountability
Research and Data Analysis Division
Olympia, WA 98504-5204

Hi Joshua:

how to do a permutation test on the following sample with the sample size in
20000 :

id        weight      P VALUE

100      100 
101       200
102       200
103       150


.......

Thanks
-- 
View this message in context:
http://r.789695.n4.nabble.com/choosing-a-random-sample-by-precentage-tp2299509p2299529.html
Sent from the R help mailing list archive at Nabble.com.

On Thu, Jul 22, 2010 at 4:11 PM, jd6688 <jdsignature at gmail.com>
wrote:
>
> Hi Joshua:
>
> how to do a permutation test on the following sample with the sample size
in
> 20000 :
Take a look at some of the results from

RSiteSearch("permutation test")

the "coin" package also comes to mind

Josh

>
> id ? ? ? ?weight ? ? ?P VALUE
>
> 100 ? ? ?100
> 101 ? ? ? 200
> 102 ? ? ? 200
> 103 ? ? ? 150
>
>
> .......
>
> Thanks
> --
> View this message in context:
http://r.789695.n4.nabble.com/choosing-a-random-sample-by-precentage-tp2299509p2299529.html
> Sent from the R help mailing list archive at Nabble.com.
>
> ______________________________________________
> 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.
>


-- 
Joshua Wiley
Ph.D. Student, Health Psychology
University of California, Los Angeles
http://www.joshuawiley.com/

Hi Ethan,

I should clarify that you do not *need* to make size an integer, so
you technically do not need trunc(), but if you use trunc() or
round(), you get to be in control of what you get.  To answer your
second question, look at this little function, it even lets you choose
different percentages.  Notice how using -random.rows, one is able to
select all BUT those rows.

Cheers,

Josh


#Data for the example
x <- matrix(1:40, ncol = 2)

my.sampler <- function(name, percentage = 10){
  random.rows <- sample(nrow(name), trunc(nrow(x)*(percentage/100)))
  x.1 <- name[random.rows, ]
  x.2 <- name[-random.rows, ]
  value <- list(x.random = x.1, x.allelse = x.2)
  return(value)
}
#So you can see
my.sampler(x)

output <- my.sampler(x)

output$x.random
output$x.allelse



On Thu, Jul 22, 2010 at 4:59 PM, Xebar Saram <zeltakc at gmail.com>
wrote:
> Wow guys
>
> thank you so much for the quick answers, i really appriciate it :)
>
> I have another question then if you dont mind. how does one proceed to
> randmomly split a single dataset into 90% and 10%?
>
> thx alot again
>
> Ethan
>
> On Thu, Jul 22, 2010 at 7:28 PM, Joshua Wiley <jwiley.psych at
gmail.com> wrote:
>> On Thu, Jul 22, 2010 at 4:11 PM, jd6688 <jdsignature at
gmail.com> wrote:
>>>
>>> Hi Joshua:
>>>
>>> how to do a permutation test on the following sample with the
sample size in
>>> 20000 :
>>
>> Take a look at some of the results from
>>
>> RSiteSearch("permutation test")
>>
>> the "coin" package also comes to mind
>>
>> Josh
>>
>>
>>>
>>> id ? ? ? ?weight ? ? ?P VALUE
>>>
>>> 100 ? ? ?100
>>> 101 ? ? ? 200
>>> 102 ? ? ? 200
>>> 103 ? ? ? 150
>>>
>>>
>>> .......
>>>
>>> Thanks
>>> --
>>> View this message in context:
http://r.789695.n4.nabble.com/choosing-a-random-sample-by-precentage-tp2299509p2299529.html
>>> Sent from the R help mailing list archive at Nabble.com.
>>>
>>> ______________________________________________
>>> 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.
>>>
>>
>>
>>
>> --
>> Joshua Wiley
>> Ph.D. Student, Health Psychology
>> University of California, Los Angeles
>> http://www.joshuawiley.com/
>>
>> ______________________________________________
>> 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.
>>
>


-- 
Joshua Wiley
Ph.D. Student, Health Psychology
University of California, Los Angeles
http://www.joshuawiley.com/