Dear R-List,
I apologize for not posting a reproducible example - the reason is that I
actually do not succeed in reproducing my specific problem with
generated data.
Let me still describe the problem:
I want to impute missing data using the "pan" package.
a) It works, when I use a fraction of my data (e.g. 200 out of 44000 cases)
b) It works, when I generate a dataset of equal size as the original
based on my empirical means and covs using "mvrnorm" package.
c) It works, when I use "norm" instead of "pan" (though I used the
stand-alone package - I do not know whether it makes a difference)
BUT R CRASHES without log after about 30 minutes whenever I try imputation on
my original dataset using "pan".
This is the code I used:
library(pan)
level2<-DF$l2.id #specify
my level 2 ID in my dataframe (DF)
subj<-match(level2,unique(level2)) #number the level
2 units from 1:n
y<-as.matrix(DF[-1])
#specify the variables to be used for imputation
pred <- matrix( rep( 1 , nrow(y) ) , ncol= 1) #specify predictor
matrix
xcol <- 1 #col
with fixed effect in pred
zcol <- 1 #col
with random effect in pred
prior <- list( a=ncol(y),
#non-informative prior
Binv= diag( rep(1,ncol(y) ) ) ,
c= ncol(y) * length(zcol) ,
Dinv= diag( rep(1 ,ncol(y)*length(zcol) ) )
)
imput1 <- pan(y,subj,pred,xcol,zcol,prior,seed= 13579 ,iter= 1000) #run first
imputation
...after 30 minutes: CRASH (R ends automatically, Rgui is closed without log)
Is there a way to identify the source of such a problem? Or any idea what could
be the problem?
Thank you in advance.
Best wishes
Alain
[[alternative HTML version deleted]]
______________________________________________
[email protected] 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.
