Re: st: sureg

[Mekbib Haile <haymakg@yahoo.com>]

Thanks, that was so helpful

 Mek


----- Original Message -----
From: Mekbib Haile <haymakg@yahoo.com>
To: "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Cc: 
Sent: Saturday, August 25, 2012 12:08 PM
Subject: st: sureg 

Dear stata users,

would you please help me on this?

1.   After a sureg command on STATA using level variables, I wanted to estimate elasticities with the margins eyex command.

I have one problem with one of my equations: stata gives me the following error message.

. margins, eyex (l2.y  l.y  x1  x2  x3) predict(equation(y))
 could not calculate numerical derivatives -- discontinuous region with missing values encountered r(459);

However,
my data has no missing values except for the lag variables. What could 
be a potential problem? The same command works fine when all the 
covariates were in logarthmic
format.  

Do you also suggest estimating elasticities at mean 
(atmeans option) values or better to use the average of the elasticities
of individual observations?

2.   How do I test and control for Heteroscedasticity after a Seemingly Unrelated Regression using STATA?


Many thanks!

Mac    


 
Mekbib Haile (PhD student)
Center for Development Research (ZEF)
University of Bonn
Walter Flex Str. 3,D-53113, Bonn, Germany
Email: mekhaile@uni-bonn.de

*
*   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/


*
*   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/