Hi to
everyone, I have a big data set where rows are observations and columns are
variables. It contains a lot of missing values. I have used multiple imputation
with library mice and I get an exact prediction of each missing value. Now, I
would like to know the error I can commit or the confidence interval.
How can I
get this?
This is
part of my code
library(mice)
mod1<-mice(dat,
method=c("","",rep("pmm",6)))
ro<-round(cor(dat,
use = "pair"), 3)
predictor<-quickpred(dat)#
esta matriz predictora se construye según las correlaciones
mod1<-mice(dat,method=c("","",rep("pmm",6)),
pred=predictor)
imputados<-complete(mod1,'long')
x.imp=split(imputados,
imputados$.imp)
acumula=x.imp[[1]][,-c(1,2)]
for(j
in 2:length(x.imp))
{
acumula=acumula+x.imp[[j]][,-c(1,2)]}
med.imp=acumula/5
Thanks in
advance
[[alternative HTML version deleted]]
______________________________________________
R-help@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.
