21 Jan
2009
21 Jan
'09
3:58 p.m.
Hi Steve,
When you load the .RData file it will put objects from the file back
into your R session. You can think of it like a moving box that
contains data frame, matrices, regression outputs, etc.
For your specific problem, once you load the RData file, you should
find "output" in your R sessions (you can see this by running ls()).
Thus, you can run the diagnostics as follows:
overimpute(data=data,output=output,var=5)
Hope that helps!
matt.
On Thu, Jan 15, 2009 at 7:01 AM, Steve Shewfelt
<steven.shewfelt(a)yale.edu> wrote:
Hello,
How does one run diagnostics based on saved output from an imputation
process (if indeed it is possible)? If the imputation takes a long time and
it is not possible to do the diagnostics immediately, can one shut down R
and return to the diagnostics later?
For example, if one does an imputation of the following sort:
-
Amelia mailing list served by Harvard-MIT Data Center
[Un]Subscribe/View Archive: http://lists.gking.harvard.edu/?info=amelia
More info about Amelia: http://gking.harvard.edu/amelia
output=amelia(data=data,m=5,archive=TRUE,outname="imputed",write.out=TRUE,keep.data=TRUE)
And then saves the output as follows:
save(output,file="out.rData")
And then shuts down R to return at a later date to the diagnostics, how
would you go about completing the following command line:
overimpute(data=data,output=????,var=5)
I guess this is in some sense a question about how to read in an ".rData"
data frame properly.
Thank you in advance,
Steve Shewfelt
PhD Candidate
Department of Political Science
Yale University
-
Amelia mailing list served by Harvard-MIT Data Center
[Un]Subscribe/View Archive: http://lists.gking.harvard.edu/?info=amelia
More info about Amelia: http://gking.harvard.edu/amelia