st: RE: Question on the xtdpd command

["Martin Weiss" <martin.weiss1@gmx.de>]

<>

You can also try this using the official examples:


***********
webuse abdata, clear

//no gaps
xtdes
xtdpd l(0/2).n l(0/1).(w ys) k, dgmmiv(n) div(l(0/1).(w ys) k) fod

//create gaps
set seed 10010
drop if runiform()<.02
xtdes
//-xtdpd- starts complaining
xtdpd l(0/2).n l(0/1).(w ys) k, dgmmiv(n) div(l(0/1).(w ys) k) fod
***********


HTH
Martin

-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of Narasimhan
Sowmyanarayanan
Sent: Samstag, 4. September 2010 22:07
To: statalist@hsphsun2.harvard.edu
Subject: st: Question on the xtdpd command

I have a query on the xtdpd command and the specific use of the fod
option to use forward orthogonal deviations as the instrument. In the
specific dataset I am trying to use the fod option, I get the message
"fodeviation is not allowed when there are gaps in the data."  While I
have an unbalanced panel, I did not find any gaps in the data in the
panel. Further, when I do xtset, it does not give me any message that
there are gaps in the panel. My limited experience with this is that
one can estimate the fod option with unbalanced panels ? Atleast this
is what I read in the Roodman (2009) paper in stata journal on How to
do xtabond2. I would appreciate any insights someone can provide on
this. I am not estimating a levels model. Also, I tried using the fod
option using a mock dataset "mus08psidextract.dta"  from Cameron and
Trivedi's most recent textbook with the fod option. That works fine.
the data is a balanced panel though.

Thanks for your time and attention in advance.

Sincerely,
*
*   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/