Statalist


[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]

Re: st: Xthtaylor


From   "Rodrigo Alfaro" <raalfaroa@gmail.com>
To   statalist@hsphsun2.harvard.edu, tamdphan@gmail.com
Subject   Re: st: Xthtaylor
Date   Thu, 6 Dec 2007 10:56:38 -0300

Nicola,

Tam wants to use -xthtaylor- with the option am (for Amemiya-
MaCurdy) but the ado only allows for balanced-panels.

I suggest to run HT "by hand", I proposed this before:

http://www.stata.com/statalist/archive/2007-02/msg00082.html
http://www.stata.com/statalist/archive/2007-07/msg00769.html

I don't see any problem with running the third step (IV) for
unbalanced panels. Maybe there is some problems if the
unbalanceness is not mild. I guess that for a large
Ahrens and Pincus index (defined as Harmonic Average
of Periods / Arithmetic Average of Periods) the results
hold as the same as balanced case.

Rodrigo.


On Dec 3, 2007 2:00 PM,  <nicola.baldini2@unibo.it> wrote:
> I don't understand this question. What's wrong for the default option (Hausman-Taylor estimator)?
> Nicola
> At 02.33 30/11/2007 -0500, "Tam Phan" wrote:
> >I noticed that xthtaylor only runs amemiya-macurdy estimator for
> >balanced panel data.
> >Is there one for unbalanced?
>
>
> *
> *   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/



© Copyright 1996–2021 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index