Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: Urgent-Help


From   Austin Nichols <austinnichols@gmail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: Urgent-Help
Date   Thu, 25 Feb 2010 16:18:00 -0500

A. Sen <as934@cam.ac.uk> :
Read the help file for -xtoverid- (on SSC) for a generalized Hausman
test that you might adapt to MI.
http://fmwww.bc.edu/repec/bocode/x/xtoverid.html
You can also get the e(b) and e(V) in each imputation for FE and RE
and combine yourself by hand.

On Thu, Feb 25, 2010 at 1:01 PM, A. Sen <as934@cam.ac.uk> wrote:
> Hi
>
> I am from the University of Cambridge and this question is regarding STATA11
> and its mi command. I hope you can help me out with this as noone else has
> been able to.
>
> I have 5 imputed datasets and I am estimating random effects and fixed
> effects models for the panel data I have. To choose between these two, i
> need to perform a hausman specification test. I estimate the RE model first
> and store estimates- estimates store random. I then estimate the FE model
> and go to postestimation and run the hausman test. But the error message is
> - e(b) not found in random. This e(b) and e(v) not found prevents me from
> presenting the results in a table as well. i have tried cmdok as well but
> nothing seems to work. Can you please provide me with a command which allows
> me to carry out this test.
>
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index