Hello Tim,
Sorry for the late reply, but I wanted to address your concern about
overimputation. Currently, we don't support overimputation for nominal
variables. I'm terribly sorry that the error message was unclear about
that. We'll update that and in the future we might extend overimpute to
handle nominals variables as well. Sorry for any inconvenience and good
luck with your project.
best,
matt.
On Thu, 8 Mar 2007, Tim Müllenborn wrote:
Hallo Gary,
And al the others of the list.
First of al, thanks for the fast replay.
My problem in short: when I mark a polytomous nominal variable (party
affiliation)in my dataset as "nominal" in Amelia view and I want to
overimpute it Amelia tells me that "The variable you selected doesn't exist
in the Amelia output because it wasn't imputed". However, when I select
"compare" Amelia shows me the density of the observed and the imputed values
as well.
What Im using:
R: Version 2.4.0
Amelia: latest Version
What i have done so fare:
I am using a dataset from Iversen and Soskice (2001) which is available
online at:
http://www.people.fas.harvard.edu/~iversen/data/preferences.htm => Dataset 1
I dropt the variables v23, v26, v30, v31 which are combined to the index "P"
in the dataset. The same I have done with variables v25 v32, which are
combined to the index "Postmat".
The resulting dataset I have loaded in AmeliaView. Then I have selected
"Nominal" for variable v223 in the "Variables" Dialog box which is
the party
affiliation variable I mentioned. When I start the imputation, it runs quite
well.
Best wishes,
Tim
-
Amelia mailing list served by Harvard-MIT Data Center
[Un]Subscribe/View Archive:
http://lists.gking.harvard.edu/?info=amelia