Thank you Kit. That explains it!
Davide
2008/8/10 Kit Baum <[email protected]>:
> < >
>
> Davide said
>
> cap program drop testlreff
>
> program testlreff
> nlcom _b[L1.x]/(1-_b[L1.y])
> mat b1=r(b)
> mat v1=r(V)
> local b=b1[1,1]
> local se=sqrt(v1[1,1])
> end
>
> xtabond2 y L.(y x) yr* , gmm(L.(y)) iv(yr*) iv(L2.x, passthru) noleveleq
> robust
> testlreff
> outreg2 L1.y L1.x using whatever, bdec(3) br addstat(long-run effect,
> `b', se, `se') replace
>
> *** code ends here***
>
> The problem that appears when I run this do file is that right after
> the outreg-line Stata stops and tells me:
>
> . outreg2 L1.y L1.x using whatever.xls, bdec(3) br addstat(lon
>> g-run effect, `b', se, `se')
> invalid syntax
> r(198);
>
>
>
>
> Your program testlreff does not return anything to the calling program.
> Items b and se are local to testlreff. This may work in interactive mode as
> you are defining locals that are then visible to the next command, but it
> will not when this routine is in a do-file. If you modify the last two lines
> to read
>
> return local b = b[1,1]
> return local se = sqrt(v1[1,1])
>
> you then should have access to those objects, which will be known as r(b)
> and r(se). Also modify the program line to read
>
> program testlreff, rclass
>
>
> Kit Baum, Boston College Economics and DIW Berlin
> http://ideas.repec.org/e/pba1.html
> An Introduction to Modern Econometrics Using Stata:
> http://www.stata-press.com/books/imeus.html
>
>
> *
> * 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/
