meganweil wrote (modulo deprecated MIME/HTML)
Question: Is there a way to use the 'Outreg' command after
using the 'Repeat Stata command'?
This is my first posting so forgive me if I don't know the
'right' way to ask my question.
Details: I am using multiple linear regression for twenty
different dependent outcomes variables. There are several
different 'models' I am looking at, which are consistent
across the outcomes. For each model, the independent
variables are all the same. So rather than type each
equation separately I am using the Repeat Stata command
for each model. Now I need to compare different models
for the outcome variables. So for each outcome variable,
I would like to look at the beta coefficient and confidence
interval for the first independent variable for each model.
My output would ideally look something like the following:
Test A Score: Model 1 Model 2 Model 3
blood lead beta1 beta2 beta3
(CI1) (CI2) (CI3)
age beta2a beta3a
(CI2a) (CI3a)
gender beta3b
(CI3b)
Test B Score: Model 1 Model 2 Model 3
blood lead beta1 beta2 beta3
(CI1) (CI2) (CI3)
age beta2a beta3a
(CI2a) (CI3a)
gender beta3b
(CI3b)
The problem is after typing the command:
for testa testb: regress X
. . . if I then use the outreg command it only captures the
last regression. Is there a way to use outreg to capture
all of the regressions?
>>> I've never used -outreg- but I know something about
-for-. You can get separate reports on each regression
by putting a call to -outreg- within the -for- command
(or -- much much better -- using -foreach-).
I'm not aware that -outreg- will combine model
results in the way that you wish. Someone confirm
or refute!
Roger Newson's programs offer a different approach,
as he may well explain.
Nick
[email protected]
*
* 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/
