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: estimated dependent variable with xtmixed


From   Jeph Herrin <stata@spandrel.net>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: estimated dependent variable with xtmixed
Date   Thu, 20 Jun 2013 20:33:31 -0400

Unfortunately, xtmixed does not support these kind of weights. This model is called "V-known" and the only way I have found to estimate it is to use the software package HLM. I have heard that this model is equivalent to putting SE(Y) in the model as a covariate, but I haven't been able to convince myself of that.

hth,
Jeph


On 6/20/2013 5:17 PM, Alexandru Cojocaru wrote:
I would like to estimate a model of the following form:

Y_ij=X_ij*b+u_i+e_ij,
where Y_ij is the municipal poverty rate (from a household survey)
X_ij are municipal characteristics (from a population Census)
u_i are the region level random effects (municipalities are nested
within regions).

With xtmixed, this would look like: xtmixed mun_pov X_ij || region:
Since municipal poverty rates are sample estimates, they have
corresponding sampling variances. How would one properly incorporate
this uncertainty into the xtmixed setup?

Any advice would be much appreciated.

cheers,
Sandu
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/faqs/resources/statalist-faq/
*   http://www.ats.ucla.edu/stat/stata/


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