Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

st: Re: errors in covariates in an ordered logit


From   "Sophia Rabe-Hesketh" <spaksrh@iop.kcl.ac.uk>
To   <statalist@hsphsun2.harvard.edu>
Subject   st: Re: errors in covariates in an ordered logit
Date   Mon, 28 Jul 2003 12:38:11 -0700

Hi Eric Verhoogen,

You can probably use gllamm (gllamm6 is out-of-date
now) or one of the programs recently developed by Hardin, 
Carroll and Schmiediche, see http://www.stata.com/merror/
There is also a draft article on that site on using gllamm for
maximum likelihood estimation of covariate measurement error
models. 

Your problem seems to be a bit different from the ones we
describe in that paper since you do not seem to have replicate 
measurements of the covariate that's measured with error. 
However, you should still be able to use gllamm if you  
constrain the measurement error variance to a known constant. 
Does the within-group covariance apply to the true covariate 
or to the measurement errors? gllamm should be able to handle 
such a 'multilevel' structure as well. Please email me privately 
if you need specific help.

The most recent version of gllamm is available from
http://www.iop.kcl.ac.uk/IoP/Departments/BioComp/programs/gllamm.html

Best regards,

Sophia

----- Original Message ----- 
From: "Eric Verhoogen" <everhoogen@yahoo.com>
To: <statalist@hsphsun2.harvard.edu>
Sent: Monday, July 28, 2003 7:09 AM
Subject: st: errors in covariates in an ordered logit


> Hi everyone --
> I am running an ordered logit and one of my covariates
> in measured with error. I can specify its
> variance-covariance matrix. (There is some covariance
> for the covariate across different observations,
> within groups.) It looks like the command gllamm6
> (from package sq129 published in STB 53) might be able
> to handle this, but I cannot tell from the
> documentation how to do it. Can anyone help me with
> this?
> Thanks,
> Eric Verhoogen
> everhoog@econ.berkeley.edu
> everhoogen@yahoo.com
> 
> =====
> Eric Verhoogen
> Department of Economics
> University of California, Berkeley
> everhoog@econ.berkeley.edu
> everhoogen@yahoo.com
> 
> __________________________________________________
> Do You Yahoo!?
> Yahoo! Greetings - Send FREE e-cards for every occasion!
> http://greetings.yahoo.com
> 
> *
> *   For searches and help try:
> *   http://www.stata.com/support/faqs/res/findit.html
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/
> 
> 
> *
> *   For searches and help try:
> *   http://www.stata.com/support/faqs/res/findit.html
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/
*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   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   |   What's new   |   Site index