Stata The Stata listserver
[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: lags of the x's in xtabond


From   Giovanni Bruno <giovanni.bruno@unibocconi.it>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: lags of the x's in xtabond
Date   Tue, 4 May 2004 12:32:06 +0200

Tewodaj,

It seems to me that

1.  xtabond   y ,  lags(1)  pre(x, lag(1,1) )
2.  xtabond   y ,  lags(1)  pre(x lag_x, lag(0,1) )

actually provide different estimators for the same model:

y(it) =   y(i t-1)   +   x(it)  +   x(i t-1)  +   e(it).

While method 1 includes L1.x (but not further lags) as instruments, method 2
includes both L1.x and L1.lag_x, which is L2.x, as instruments. This also
explains why method 2. is equivalent to

3. xtabond   y ,  lags(1)  pre(x, lag(1,2) )

which still considers the same model but includes L1.x and L2.x as
instruments, exactly as method 2.

Giovanni

TEWODAJ MOGUES <tmogues@students.wisc.edu>:
> Hi Stata users,
>
> I am setting up a distributed lag model in xtabond, and I am a bit puzzled
> about what xtabond is doing exactly when I restrict the instrument set of the
> distributed lags.
>
> Say I want to model:
> y(it) =   y(i t-1)   +   x(it)  +   x(i t-1)  +   e(it)
> where x is a predetermined variable. Suppose I want to restrict the
> instrumens of x to just one further lag of x. There are two ways to write the
> command, and they should be identical:
>
> 1.  xtabond   y ,  lags(1)  pre(x, lag(1,1) )
> 2.  xtabond   y ,  lags(1)  pre(x lag_x, lag(0,1) )
>
> where lag_x is a variable I created by typing:
> generate lag_x = L.x
> These two commands give different results, which is puzzling. On the other
> hand, 2. gives, strangely enough, identical results to the following
> command:
> 3.  xtabond   y ,  lags(1)  pre(x, lag(1,2) )
>
> My question is: If I want to restrict the instruments of x to just one lag,
> which of the commands above should I use? Asked more open-endedly: What is it
> that 1. is doing versus that which 2. and 3. are doing in terms of the
> instrument set they are setting up?
>
> Thanks for any thoughts on this.
> Tewodaj
>
> ~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~.~
> Tewodaj Mogues
> Dept. of Agricultural and Applied Economics
> University of Wisconsin - Madison
> 427 Lorch St. #317, Taylor Hall
> Madison, WI 53706
>
> *
> *   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/
>


-- 
Giovanni Bruno
Istituto di Economia Politica, UniversitÓ Bocconi
Via U. Gobbi, 5, 20136 Milano
Italy
tel. + 02 5836 5411
fax. + 02 5836 5438

*
*   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/



© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index