[R] test wilcoxon sur R help!

[Rui Barradas]

Hello,

There's a bug in your function, it should be 'dat', not 'dat1'. In the 
line marked, below.

fun1 <- function(dat){
	mat1 <- combn(colnames(dat),2)  # Here, 'dat' not 'dat1'
	res <- sapply(seq_len(ncol(mat1)),function(i) {x1<- dat[,mat1[,i]]; 
wilcox.test(x1[,1],x1[,2])$p.value})
	names(res) <- apply(mat1,2,paste,collapse="_")
	res
}


Hope this helps,

Rui Barradas

Em 24-10-2013 20:16, arun escreveu:
> Hi,
> Try:
> fun1 <- function(dat){
> mat1 <- combn(colnames(dat1),2)
>   res <- sapply(seq_len(ncol(mat1)),function(i) {x1<- dat[,mat1[,i]]; wilcox.test(x1[,1],x1[,2])$p.value})
> names(res) <- apply(mat1,2,paste,collapse="_")
> res
> }
>
> set.seed(432)
> dat1 <- as.data.frame(matrix(sample(18*10,18*10,replace=FALSE),ncol=18))
>
>    fun1(dat1) #gives the p-value for each pair of columns
>
>
>
>
> Hi,
>
> I want to make a wilcoxon test, i have 18 columns each column
> corresponds to a different sample and i want to compare one to each
> other with a wilcoxon test in one step this is possible ? or do i
> compare two by tow?
>
> Does it exist a code for automation this test? like this i dont have to type the code for each couple.
>
> thanks!
> denisse
>
> ______________________________________________
> 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.
>