Amelia for Gauss saves files in standard Gauss dataset format. just load
them up and print them out. since these are Gauss commands and not Amelia
commands, you will have to look at the Gauss manual rather than Amelia for
details.
Your code looks ok to me, but make sure the imputations make sense of
course.
And on your last point, if you've registered for our listserv, that's all
you need to do; you're signed up.
Best of luck with your research,
Gary King
---
Gary King
Institute for Quantitative Social Science
Harvard University, 34 Kirkland St, Cambridge, MA 02138
http://GKing.Harvard.Edu, email: King(a)Harvard.Edu
Direct 617-495-2027, Assistant 495-9271, eFax 812-8581
On Thu, 5 May 2005, Gary King wrote:
---------- Forwarded message ----------
Date: Thu, 5 May 2005 12:40:14 -0700
From: Sanjoy Bhattacharjee <bhutu1(a)gmail.com>
To: King(a)Harvard.edu
Subject: regarding Amelia!_GAUSS mode
Prof. Gary King
Respected Sir,
I found your "Amelia" at the time when it's most needed ... a mere thanks
will thus not be enough, my heartfelt and sincere gratitude to u and ur
other colleagues ... for writing program like this and of course, mainly
because of making it available to the world of Internet
as a primary run it works nicely ... mine is GAUSS version 6.0, Windows
XP-prof
I have two quick questions
Q1. I want to look at the "imputed data set" that "Amelia" makes
after each
successful run ... by default in GAUSS it makes in ".dat" format ... What
should I do, I have tried in different ways, but could not get to look at
them ... could you help me please ..say one of the file name that Amelia
makes after successful runnning is c:\gauss6.0\impute1.dat
Q2. Kindley check my code and tell me what I have done is correct or not ...
oh! four variables of my data set are categorical on the scale of 1 to 5
new;
cls;
load y[240,8] = d:\missing.txt;
dataset = "IMPUTE";
vnames = { x1, x2, x3, x4, x5, x6, x7, x8 };
c = saved(y,dataset,vnames);
library amelia; /* initialize Amelia */
_ AMnds=10; /* no. of imputations, default is 5*/
_ AMprt=1; /*1 is in fact the default value, print output and intermediate
results to the screen*/
_ AMfully={1,2,3,4}; /* variables those do NOT have any missing value*/
_ AMords={5,6,7,8}; /* variables those do have missing value*/
_ AMordmd=0;
_ AMempri=3; /*use ridge prior*/
dbuf = amelia("IMPUTE"); /* impute and save m=10 imputed datasets */
save dbuf;
end;
Thanks and regards ...Sanjoy
* I have registered into the Amelia group, but could not find exactly whom
to send ... my registration id is "bhutudse(a)yahoo.com"
--
Sanjoy Bhattacharjee
PhD student
School of Economic Sciences
Washington State University
Hulbert Hall, 207E
Pullman, WA 99164
"Life is the art of drawing sufficient conclusions from insufficient
premises" - Samuel Butler
-
Amelia mailing list served by Harvard-MIT Data Center
[Un]Subscribe/View Archive:
http://lists.hmdc.harvard.edu/?info=amelia
-
Amelia mailing list served by Harvard-MIT Data Center
[Un]Subscribe/View Archive:
http://lists.hmdc.harvard.edu/?info=amelia