Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: AGAIN: omit output of some coefficients with outreg2


From   "Paulo Regis" <pauloregis.ar@googlemail.com>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: AGAIN: omit output of some coefficients with outreg2
Date   Sat, 24 May 2008 21:00:01 +0100

Roy,

In the past two weeks, I have been working with -outreg2 (great
command!!). I must say many times I even prefer to print out text
files from outreg2 output than log files. In my opinion, the drop
option will be very useful (as long as the variable is not dropped
from the database) since the positively drop happen quite often (far
from occasionally, in my experience).

Also, I may suggest you take into account to improve the "label"
option. Many times I prefer -outreg to -outreg2 since you can use
labels and coefficient of variables with different names are displayed
in the same row. Actually, the help file of -outreg2 says you can do
this but it is not true. When you specify "label", an extra column is
added with the name of the labels which is something completely
different. If labels remains as it is now, then the help file should
be modified.

Something that may be useful for stata users is to be able to include
text in each column. Up to now, you can use the option -ctitle() (and
it is what I am doing but it has the limitation it only allows to
introduce information in one row per column). The option addstat()
does not allow text. I can introduce an extra value per row and as
many rows as possible but I would like to introduce text as well. Is
it difficult to introduce something like an addtext() option?

Maybe, I can give you an example why addtext() can be useful. One of
my regressors is a forecast of variable x1 and I have more than 10
methods to perform the forecast (I am using factors). I would like to
choose the most convenient forecast based AIC. What I am doing is to
print only the output from selected forecast method and using ctitle()
to know which one is it.

Cheers,

Paulo

On Sat, May 24, 2008 at 11:58 AM, John Bunge <jota.be@web.de> wrote:
>
> a drop option would be helpful
>
> thanks for the effort!
>
> John.
>
>
> > -----Ursprüngliche Nachricht-----
> > Von: statalist@hsphsun2.harvard.edu
> > Gesendet: 23.05.08 22:56:23
> > An: <statalist@hsphsun2.harvard.edu>
> > Betreff: st: AGAIN: omit output of some coefficients with outreg2
>
>
> > >you proposed to type outreg2 a b using myfile, which works
> > >perfect. now imagine i have 20 regressors a1 to a20 but want
> > >to omit the result for a20. do i have to type outreg2 a1 a2 a3
> > >... a19 using myfile or is there an easier way to do it?
> >
> > In the variables are consecutive, you can try
> >
> > outreg2 a1-a19 using myfile
> >
> > But what you want to do is to "positively" drop a variable.
> > This comes up occassionally. It's the syntax that was
> > never settled on. If -drop( )- option is added, should
> > -keep( )- option be added as well? That seems redundant
> > with the current set up.
> >
> > Unless someone has a better suggestion, I will go ahead
> > and ask Kit Baum to upload a new one with -drop- and
> > -keep- options added. This should be available next month.
> >
> > Roy
> >
> > _________________________________________________________________
> > Change the world with e-mail. Join the i m Initiative from Microsoft.
> > http://im.live.com/Messenger/IM/Join/Default.aspx?source=EML_WL_ChangeWorld
> > *
> > *   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/
> >
>
> --
> John Bunge
> Debt and Finance Analysis Unit
> United Nations Conference on Trade and Development (UNCTAD)
> Palais des Nations
> 1211 Genève 10
> Switzerland
> Office: +41 229175902
> Mobile: +41 762901769
>
> ______________________________________________________________
> Jeden Monat 1 hochkarätiger maxdome-Blockbuster GRATIS!
> Exklusiv für alle WEB.DE Nutzer. http://www.blockbuster.web.de
>
>
> *
> *   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