Jim/Rui:
Strictly speaking, this is wrong. What you have described is MCAR --
missing completely at random -- not MAR. They are different! Nevertheless,
the OP seems to be similarly confused about this, so MCAR may in fact be
what what was wanted. Without further context, it is as clear as mud
Hi Adam,
Looks like you have a matrix or data frame and want to change one or
more observations to NA. I think this will do the trick:
# assume the matrix or data frame is named "ajdat"
randomNA<-function(x,nNA=1) {
dimx<-dim(x)
x[sample(1:dimx[1],nNA),sample(1:dimx[2],nNA)]<-NA
return(x)
}
Hello,
What type of data do you have? A vector? Or is it a matrix, a
data.frame, a list, etc?
Suppose it is a vector named x. Then you could do something like
rate <- 0.2
is.na(x) <- sample(length(x), rate*length(x))
At an R prompt type
?is.na
?sample
Hope this helps,
Rui Barradas
Às
Hi,
I want to simulate missing at random for my dataset. Do you know an easy way to
do it?
I want to try not to have the missing�s for the same observations. I mean if
one observation is been selected randomly to have missing I don�t want to have
all the var of the same obs missing.
I want
4 matches
Mail list logo
