Re: st: how to put both coefficient and exponentiated form in a table using estout or similar command

[carsten sauer <carsten.sauer@uni-bielefeld.de>]

Example:
sysuse auto, clear
su length, d
gen class = 1 if length<   r(mean)
replace class = 0 if length>   r(mean)
xi:nbreg rep78  foreign i.class, vce(cluster class)
su foreign if e(sample)==1&   foreign ==1
estadd scalar D1 = r(N)
esttab, s(N N_clust D1, labels("N" "Class" "foreign==1"))

You find more details about labeling in -help estout-

Carsten



Am 14.10.2011 13:30, schrieb Heekyung "Hellen" Kim:
> Thank you!
>
> Sorry for keeping asking a question.
>
> How can I label N_clust and D1 for a table (to present in my word document)?
> I found how to label variables, but couldn't find how to label stat numbers.
>
> -----Original Message-----
> From: owner-statalist@hsphsun2.harvard.edu
> [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Carsten Sauer
> Sent: Friday, October 14, 2011 4:06 AM
> To: statalist@hsphsun2.harvard.edu
> Subject: Re: st: how to put both coefficient and exponentiated form in a
> table using estout or similar command
>
> Try this example example:
> sysuse auto, clear
> su length, d
> gen class = 1 if length<    r(mean)
> replace class = 0 if length>    r(mean)
> xi:nbreg rep78  foreign i.class, vce(cluster class)
> su foreign if e(sample)==1&    foreign ==1
> estadd scalar D1 = r(N)
> esttab, s(N N_clust D1)
>
> Carsten
>
>
>
> Am 13.10.2011 23:43, schrieb Heekyung "Hellen" Kim:
> > I have a related question to -estout, again.
> >
> > I need to put the number of observations in each group of two groups in
> the
> > samples from the analysis (D=1 and D=0).  Then I have about 900 classes.
> > The "stat" command calls for only the total number of observations.  Is
> > there any way I can make estout add three rows of N's for one group, N for
> > the total number of observations, and then N for the number of classes?
> >
> > My regression looks like this:
> >
> > xi:nbreg y D i.class, vce(cluster class)
> >
> > So I want to make -estout write N for D=1, N for all, N for the number of
> > classes.
> >
> > Thank you for the answer in advance.
> >
> >
> > -----Original Message-----
> > From: owner-statalist@hsphsun2.harvard.edu
> > [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Carsten Sauer
> > Sent: Sunday, October 09, 2011 1:33 PM
> > To: statalist@hsphsun2.harvard.edu
> > Subject: Re: st: how to put both coefficient and exponentiated form in a
> > table using estout or similar command
> >
> > Try the following example:
> >
> > sysuse auto
> > nbreg rep78 price mpg
> > estadd expb
> > estout, cells(b(star fmt(2)) se(par fmt(2)) expb (par([ ])))
> > drop(lnalpha:) stats(N ll chi2, fmt(%8.0f %8.2f))
> >
> >
> >
> > Am 09.10.2011 18:44, schrieb Heekyung "Hellen" Kim:
> > > Thank you so much for the reply.
> > >
> > > I can see that I can make a table with two columns using -esttab with
> > > eform(0 1).  Is there a way for me to put the expontionated form under
> the
> > > raw coefficient in a bracket in the same column?
> > >
> > > -----Original Message-----
> > > From: owner-statalist@hsphsun2.harvard.edu
> > > [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Richard Herron
> > > Sent: Saturday, October 08, 2011 5:06 PM
> > > To: statalist@hsphsun2.harvard.edu
> > > Subject: Re: st: how to put both coefficient and exponentiated form in a
> > > table using estout or similar command
> > >
> > > Have you tried storing the regression with -eststo- then using
> > > -esttab- with the -, eform- option?
> > >
> > > Here's a like to an example on the -estout- package page:
> > > http://repec.org/bocode/e/estout/advanced.html#advanced001
> > >
> > > (The -estout- package is available from SSC:
> > > http://repec.org/bocode/e/estout/index.html)
> > >
> > > On Sat, Oct 8, 2011 at 16:39, Heekyung "Hellen" Kim<hekim@mit.edu>
> wrote:
> > > > Hi, I want to use -estout (or anything like that) to have a result
> table.
> > > > I am using xtnbreg or nbreg.  I want to put both coefficient and
> > > > exponentiated form in ONE table.
> > > >
> > > > I can do one of each using estout without eform for the first and estout
> > > > with eform option for expoentiated form.
> > > >
> > > > Is there any way to show both in one table ?
> > > >
> > > > estout, cells(b(star fmt(2)) se(par fmt(2))) drop(_I* o._I*) stats(N ll
> > > > chi2, fmt(%8.2f))
> > > > estout, cells(b(star fmt(2)) se(par fmt(2))) drop(_I* o._I*) stats(N ll
> > > > chi2, fmt(%8.2f)) eform
> > > >
> > > > I used the above two line to have SEPARATE tables.  I wish to have one
> > > table
> > > > containing both.
> > > >
> > > > -Helen
> > > >
> > > > *
> > > > *   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/
> > >
> > >
> > > *
> > > *   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/

--

Carsten Sauer
Soziale Ungleichheit und Sozialstrukturanalyse
Universität Bielefeld
Fakultät für Soziologie
Postfach 10 01 31
33501 Bielefeld
Tel.: 0521 106-67291/-6948 (Sekr. Frau Fischer)
Fax: 0521 106-6479

*
*   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/