Hi Andres,
Yes, you can set the minimum and maximum number of EM iterations using the
"emburn" argument. For example, this would give no less than 5 iteration
and no more than 10:
library(Amelia)
data(africa)
a.out <- amelia(africa, ts = "year", cs = "country", emburn =
c(5,10))
Hope that helps!
Cheers,
Matt
~~~~~~~~~~~
Matthew Blackwell
Assistant Professor of Government
Harvard University
url:
http://www.mattblackwell.org
On Tue, Mar 31, 2015 at 8:24 AM, Andres Colubri <andres(a)broadinstitute.org>
wrote:
Hi there,
In some rare occasions, Amelia is unable to converge and keeps iterating
without ever reaching the tolerance value.
I wouldn't not want to lower the tolerance since in most situations Amelia
converges to a good imputation. I'm using Amelia within a larger automated
pipeline that exhaustively tests different models, so the non-converging
situations, although rare, happen from time to time and require manual
intervention to stop the Amelia instance, restart the pipeline, etc.
Is is possible to set a maximum number of iterations so that Amelia can
quit the EM loop before reaching the desired tolerance? I revised the
documentation, but didn't find such an argument.
Thanks!
Andres
--
Amelia mailing list served by HUIT
[Un]Subscribe/View Archive:
http://lists.gking.harvard.edu/?info=amelia
More info about Amelia:
http://gking.harvard.edu/amelia
Amelia mailing list
Amelia(a)lists.gking.harvard.edu
To unsubscribe from this list or get other information:
https://lists.gking.harvard.edu/mailman/listinfo/amelia