Niko,
I believe the issue is that the instruments matrix is not constructed
exactly the same way in both cases.
With < iv(l2.X1, equ(level)) iv(l2d.X1, equ(diff)) >, the instruments
for the levels equation and for the FD equation are in separate columns.
With < iv(l2.X1, equ(both)) > they're in the same column.
Does the instruments matrix have one more column in the first case than
in the second case?
Jean
> -----Original Message-----
> From: [email protected]
> [mailto:[email protected]] On Behalf Of Niko Wrede
> Sent: Monday, January 16, 2006 9:36 AM
> To: [email protected]
> Subject: st: xtabond2: Proper use of ivstyle(.)
>
> I am using xtabond2 and I want to use the ivstyle supoptions
> equ(level) and
> equ(diff) in the proper way.
> Therefore I thought that following commands should produce
> the same results:
>
> xtabond2 Depvar l2.Depvar l2.X1, gmm(Depvar, lag(3 .)
> equ(both)) iv(l2.X1,
> equ(both)) twostep arte(3) small rob
>
> IS EQUAL TO
>
> xtabond2 Depvar l2.Depvar l2.X1, gmm(Depvar, lag(3 .)
> equ(both)) iv(l2.X1,
> equ(level)) iv(l2d.X1, equ(diff)) twostep arte(3) small rob
>
>
> OR PUT IN ANOTHER WAY
>
> ... iv(l2.X1, equ(both)) ... IS THE SAME AS ... iv(l2.X1,
> equ(level)) iv(l2d.X1, equ(diff)) ...
>
> Reason: Help file of xtabond2 says for the equ(both) command
> that "... Also by default, the instruments are
> first-differenced for use in the
> first-difference equations and taken as is for
> instrumenting the levels equations. "
>
> However, results differ. Does anybody know, when the extended
> version with iv( ., equ(level)) and iv(., equ(diff))
> generates the same results as the iv(., equ(both)) command?
>
> Many thanks in advance
> Niko
>
>
> *
> * 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/
