Hi all,
I do not have a licence for stata to combine the imputations for amelia. I have thought about using an aggregate function in SPSS to generate means and standard deviations for cases across all the five files (My gut instinct is that this is way too simple). I have also thought about using NORM to combine the five file parameters (Again seems to simple). Any advice on how to combine the amelia data files without stata would be much appreciated.
Kind regards Paul
I imputed six missing values (out of 672) with Amelia. There were five
complete columns used to form the imputation model (the IVs), and there
were eight DV columns, each with six missing values (an attempt with more
DVs failed). I used all default program settings to produce five
imputation sets (6 missing data points x 8 variables x 5 sets), which were
averaged to get one set of 6x8 imputed values.
Is it appropriate to operate on eight variables at once?
Are the default program settings appropriate for this example?
Thank you.
Hello,
My name is Hye-Jin Paek, a dissertator in School of Journalism and Mass Communication at UW-Madison.
I was trying to use Amelia to treat missing values for my data for mu dissertation. I downloaded the program form your website and
opened amlial.exe. Nothing comes up except the two lines:
LHA's SFX 2.54 s <c> Yoshi, 1992
AMELIA.BAT overwrite [Y/N]
it doesn't do anything whenever i click " enter," will not do anything either whether I chose "Y" or "N".
I read your article, amlia manual and listened to interactive video and guess that this is not the right program or right command i should encounter... Isn't the program that I should use? What do i miss here? I'd really appreciate your reply with some specific instructions..
Sincerely,
Hye-Jin
Dear Amelia Help,
I know that I should not use variables in an analysis that were not used in
the imputation phase. That being said, is it possible to generate new
variables based on linear transformations of the imputed variables, and use
the newly generated variables in the analysis? For example, if I impute
values for var1 and var2, can I create var3=var1+var2 and use only var3 in the
analysis, without compromising the integrity of the dataset?
Thank you,
Gina
Gina Yannitell Reinhardt
Political Science Doctoral Candidate
Washington University, St. Louis
One Brookings Drive, Box 1063
St. Louis, MO 63130
phone (314)935-5654
fax (314)935-5856
-
Amelia mailing list served by Harvard-MIT Data Center
[Un]Subscribe/View Archive: http://lists.hmdc.harvard.edu/?info=amelia
-----Original Message-----
From: Gary King [mailto:king@harvard.edu]
Sent: Thursday, November 11, 2004 3:31 PM
To: Dagmar Radin
Subject: Re: amelia
I'm out of town presently; can you send email to the amelia list and one of
my colleagues or I (after I get back) will figure it out? sorry for th
troubles. thanks, Gary
On Thu, 11 Nov 2004, Dagmar Radin wrote:
>
> Dr. King,
>
> I am a graduate student working on a paper and trying to use Amelia.
> Emailing you was my last resort, as I have not been able to move
> forward past some problems I am having. I read through the pdf file
> several times, and the help menus, but things are not working out. I
> have cross secitonal time series data with a number of missing
> observations for different variables.
>
> When I try to run the imputations, I get a message stating there are
> insufficient observations for estimation, and that I need to use prior
> or increase prior if already used. I tried to increase the prior
> (AMempri) to more than zero, but the program states that the AMfully
> is not properly defined and that I have more defined variables than
> there really are, despite the fact that I specified only 2 or 3 out of
> 26 variables that have full values. For some reason the program
> changes the AMfully definitions on its own. When I try to specify the
> AMfully again, it tells me I need to define a different value for
> AMempri. It is almost a circular problem.
>
> I am sorry to bother you, but I have run out of resources on my own
> and nobody in my department seems to have used Amelia or if they did,
> they never had such problem. Where should I look next?
>
> Thank you. Regards,
>
> Dasha
>
>
>
>
>
>
>