<>
You could use Maarten`s -indeplist- tp identify valid covariates. Strangely,
-drop(o*)- does not do the job, so let`s instead -keep-...
*********
clear*
set obs 10000
gen x1=rnormal()
gen x2=x1
gen y= 1+x1+ x2+ rnormal()
reg y x?
capt which indeplist
if _rc ssc install indeplist
indeplist
outreg2 using myfile, replace keep(`r(X)')
********
HTH
Martin
-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of sdm1
Sent: Donnerstag, 19. November 2009 18:42
To: [email protected]
Subject: st: Outreg2 and co-linear variables in a regression
I'm using outreg2 to write some regression results to a spreadsheet. In the
regression, some of the variables are co-linear and so Stata (MP11) omits
these from the regression. Is there a way to prevent outreg2 from writing
these omitted variables to the spreadsheet (it prefixes the variable names
with 'o.' and gives them a zero coefficient and standard error) without
dropping them from the regression specification?
Thanks.
Steve
*
* 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/
