James Baldwin <[email protected]>:
As -help nlcom- states, -nlcom- does not change estimation results in
e() by default. But if you specify the -post- option e.g.
eststo r1lr: nlcom (nly: _b[y]/(1-(_b[l1.x]))) (nlz:
_b[z]/(1-(_b[l1.x])) , post
then -nlcom- will post its estimates to e(b) and e(V) where -estout-
can see them. BTW, are you using the latest version of estout? The
prefix is now -eststo- not -esto- and you might find -esttab- a
convenient shortcut for writing out a table.
On Sun, May 4, 2008 at 10:17 PM, James Baldwin <[email protected]> wrote:
> I am attempting to dump the results of 8 sets of three regressions which use
> nlcom to calculate long run effects for each regression. I would like to
> generate latex formated tables using estout to automate dumping the results
> (b, se, p )into one table of short and long run effects for each set of
> regressions. It seems that estout is not friendly with nlcom and my
> searches for work arounds are turning up empty. Is there a way to dump
> results from nlcom into something useful such as a latex formated or at
> least tab delimited file?
>
> my code is something like
>
> esto r1sr: xtabond x y z ...
>
> esto r1lr: nlcom (nly: _b[y]/(1-(_b[l1.x]))) (nlz: _b[z]/(1-(_b[l1.x])) ...
>
> esto r2sr: xtabond ...
> esto r2lr: nlcom ....
>
> ...
>
> estout r1sr r1lr r2sr r2lr ... using "file", style(tex) cells(b(star
> fmt(3)) se(par)) replace
>
> which gives me only the results of the abond regressions
>
> Thank for any and all assistance,
> James
>
>
>
>
>
> *
> * 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/
