R help - Sep 2004 - How to draw an observation uniformly from a given dataset?

Hi all,

I have two questions stated below:

1. How to draw an observation uniformly from a given data?

For example, I have a dataset (or dataframe) with 10 observations (with a 
set of variables) and I want to "uniformly" select an observation from
this
given dataset, that is, the probability of selecting each observation is 
1/10. 

2. How to do this "combinations"?

source vector = (1,2)
the length of the target vector = 3

My expected outputs should be: 
111, 112, 121, 122, 211, 212, 221, 222.

However, the output from the function of combinations() is only 111, 112, 
122, 222. I can not even use the function permutations() because the length 
of the target vector is larger than the lengthe of the source vector.
Could anybody tell me how to get my expected results? 

Thank you in advance.

Rui

On Wed, 8 Sep 2004 wanr at ucalgary.ca wrote:
> Hi all,
>
> I have two questions stated below:
>
> 1. How to draw an observation uniformly from a given data?
>
> For example, I have a dataset (or dataframe) with 10 observations (with a
> set of variables) and I want to "uniformly" select an observation
from this
> given dataset, that is, the probability of selecting each observation is
> 1/10.
sample(1:10,3,replace=TRUE)
>
> 2. How to do this "combinations"?
>
> source vector = (1,2)
> the length of the target vector = 3
>
> My expected outputs should be:
> 111, 112, 121, 122, 211, 212, 221, 222.
sample(c(1,2),3,replace=TRUE)

Dave
-- 
 Dave Forrest
 drf at vims.edu                                    (804)684-7900w
 drf5n at maplepark.com                             (804)642-0662h
                                   http://maplepark.com/~drf5n/

wanr at ucalgary.ca wrote:
> Hi all,
> 
> I have two questions stated below:
> 
> 1. How to draw an observation uniformly from a given data?
> 
> For example, I have a dataset (or dataframe) with 10 observations (with a 
> set of variables) and I want to "uniformly" select an observation
from this
> given dataset, that is, the probability of selecting each observation is 
> 1/10. 
Sample the indices, as in

idx <- sample(1:10, 1)
data[idx, ]
> 2. How to do this "combinations"?
> 
> source vector = (1,2)
> the length of the target vector = 3
> 
> My expected outputs should be: 
> 111, 112, 121, 122, 211, 212, 221, 222.
> 
> However, the output from the function of combinations() is only 111, 112, 
> 122, 222. I can not even use the function permutations() because the length
> of the target vector is larger than the lengthe of the source vector.
> Could anybody tell me how to get my expected results? 
> 
> Thank you in advance.
> 
> Rui
> 
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide!
http://www.R-project.org/posting-guide.html
>