Thanks for that. You are right, I am imputing too many variables for the number of
observations I have.
Ian
----- Original Message -----
From: Gary King <king(a)harvard.edu>
Date: Tuesday, November 13, 2007 9:31 am
Subject: Re: [amelia] Error message
just a guess, but it sounds like you have fewer observations than
needed
for the number of variables you have. p*(p+3)/2 is the number of
parameters, with p=num of vars. that needs to be << n.
Gary
On Tue, 13 Nov 2007, ian.a.robinson(a)studentmail.newcastle.edu.au
wrote:
Hi there,
I am new to MI and was wondering if I could obtain some help.
At the moment, I am performing MI on a dataset of size n= 200.
This appears to
work fine. However, part of my project is to
break up the data set into male (n=92) and female (n=108). When I
try and run the same MI for the male and female data sets using
the Ameila package, I get the following errors
For the male data set, the error message:
"The resulting variance matrix was not invertible. Please check
your data
for highly collinear variables.
Warning message:
In amelia.prep(data = data, m = m, idvars = idvars, empri =
empri, :
You have a small number of observations, relative
to the number,
of variables in the imputation model. Consider removing some
variables,">
and for the female data set:
"The resulting variance matrix was not invertible. Please check
your data
for highly collinear variables."
As a result, if I want to perform m = 50 imputations, R will
only provide me with
40 or so.
Have others had similar problems? If so how have you overcome
them. If not,
what can you suggest I do?
Regards,
Ian
-
Amelia mailing list served by Harvard-MIT Data Center
[Un]Subscribe/View Archive:
http://lists.gking.harvard.edu/?info=amelia>
-
Amelia mailing list served by Harvard-MIT Data Center
[Un]Subscribe/View Archive:
http://lists.gking.harvard.edu/?info=amelia -
Amelia mailing list served by Harvard-MIT Data Center
[Un]Subscribe/View Archive: