R help - Nov 2011 - Simulation over data repeatedly for four loops

Dear Contributors,

I am trying to perform a simulation over sample data,

but I need to reproduce the same simulation over 4 groups of data. My
ability with for loop is null, in particular related

to dimensions as I always get, no matter what I try,

"number of items to replace is not a multiple of replacement length"


This is what I intend to do: replicate this operation for

four times, where the index for the four groups is in the

part of the code: datiPc[[1]][,2].

I have to replicate the following code 4 times, where the

changing part is in the data from which I pick the sample,

the data that are stored in datiPc[[1]][,2].

If I had to use data for the four samples, I would substitute the 1 with a
j and replicate a loop four times, but it never worked.


My desired final outcome is a matrix with 10000 observations for each
couple of extracted samples, i.e. 8 columns of 10000 observations of means.



db<-c()

# Estrazione dei campioni dai dati di PGG e TRUST

estr1 <- c();

    estr2 <- c();

    m1<-c()

    m2<-c()

       tmp1<- data1[[1]][,2];

      tmp2<- data2[[2]][,2];

        for(i in 1:100){

estr1<-sample(tmp1, 1000, replace = TRUE)

        estr2<-sample(tmp2, 1000, replace = TRUE)


        m1[i]<-mean(estr1,na.rm=TRUE)

        m2[i]<-mean(estr2,na.rm=TRUE)

}

db<-data.frame(cbind(m1,m2))
Thanks for any help you can provide.
Best Regards

-- 

Francesca
------------------------------

	[[alternative HTML version deleted]]

Perhaps you might want to abstract your code a bit and try something like:

X = rnorm(500) # Some Data
replicate(1e4, mean(sample(X, 500, replace = T)))

Obviously you can set up a loop over your data sets as needed.

Michael

On Sat, Nov 12, 2011 at 6:46 PM, Francesca <francesca.pancotto at
gmail.com> wrote:
> Dear Contributors,
>
> I am trying to perform a simulation over sample data,
>
> but I need to reproduce the same simulation over 4 groups of data. My
> ability with for loop is null, in particular related
>
> to dimensions as I always get, no matter what I try,
>
> "number of items to replace is not a multiple of replacement
length"
>
>
> This is what I intend to do: replicate this operation for
>
> four times, where the index for the four groups is in the
>
> part of the code: datiPc[[1]][,2].
>
> I have to replicate the following code 4 times, where the
>
> changing part is in the data from which I pick the sample,
>
> the data that are stored in datiPc[[1]][,2].
>
> If I had to use data for the four samples, I would substitute the 1 with a
> j and replicate a loop four times, but it never worked.
>
>
> My desired final outcome is a matrix with 10000 observations for each
> couple of extracted samples, i.e. 8 columns of 10000 observations of means.
>
>
>
> db<-c()
>
> # Estrazione dei campioni dai dati di PGG e TRUST
>
> estr1 <- c();
>
> ? ?estr2 <- c();
>
> ? ?m1<-c()
>
> ? ?m2<-c()
>
> ? ? ? tmp1<- data1[[1]][,2];
>
> ? ? ?tmp2<- data2[[2]][,2];
>
> ? ? ? ?for(i in 1:100){
>
> estr1<-sample(tmp1, 1000, replace = TRUE)
>
> ? ? ? ?estr2<-sample(tmp2, 1000, replace = TRUE)
>
>
> ? ? ? ?m1[i]<-mean(estr1,na.rm=TRUE)
>
> ? ? ? ?m2[i]<-mean(estr2,na.rm=TRUE)
>
> }
>
> db<-data.frame(cbind(m1,m2))
> Thanks for any help you can provide.
> Best Regards
>
> --
>
> Francesca
> ------------------------------
>
> ? ? ? ?[[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.
>