Joe,
You might try -lincom-.
For example:
. sysuse auto
(1978 Automobile Data)
. qui reg weight mpg
. local a = _b[mpg]
. qui reg price mpg
. lincom mpg + `a'
( 1) mpg = 108.4316
---------------------------------------------------------------------------
price | Coef. Std. Err. t P>|t| [95% Conf.
Interval]
-------------+-------------------------------------------------------------
(1) | -347.3259 53.07669 -6.54 0.000 -453.1323
-241.5195
---------------------------------------------------------------------------
Hope this helps,
Scott
-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of joe J.
Sent: Saturday, July 03, 2004 12:20 AM
To: [email protected]
Subject: st: Post estimation
Sorry for any double posting.
I want to estimate two equations (fixed effect panel) with the same set of
independent variables. My final coefficients and t values would be as
follows,
1. Final coefficients: the sum of the coefficients from the two equations
2. Final t value: Summed coefficient (of equations 1&2)/Standard Error of
the second equation
I know that using matrix command I can add coefficients from both eqautions.
But I have not been able to figure out how to extract Standard Error from
the second equation and combine that with the summed coefficient (generated
from adding up coefficients of equation 1 and 2).
Any hint would be of great help.
Joe
*
* 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/
