It is the way the instruments are treated.
This is well explained in the help to xtabond2
-help xtabond2- and search for collapse
Eric de Souza
College of Europe
Brugge (Bruges), Belgium
http://www.coleurope.eu
-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of 21443017
Sent: 05 August 2009 10:54
To: [email protected]
Subject: st: Collapse in Gmm
Dear All,
I am using -xtabond2- to run GMM-estimation. Below is the code I used
xi:xtabond2 y L.y x1 x2 x3 i.industry i.year, gmmstyle (y x1 x2 x3,
lag(3
5) collapse) ivstyle(i.industry i.year) twostep robust small
However, I also tried
xi:xtabond2 y L.y x1 x2 x3 i.industry i.year, gmmstyle (y x1 x2 x3,
lag(3
5)) ivstyle(i.industry i.year) twostep robust small
Although the results are quite consistent, I was just wondering why the
results are different from including the -collaspe- and not.
Many Thanks
Best Wishes
Wenwen
*
* 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/
