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

st: I am new in the list, (doubts on Xtabond)

From   "Lopez Noria, Gabriela" <[email protected]>
To   <[email protected]>
Subject   st: I am new in the list, (doubts on Xtabond)
Date   Wed, 11 Aug 2004 15:57:26 +0100

My name is Gabriela Lopez.   I want to calculate total factor
productivity but in the papers I have read the authors first use the
General Method of Moments.   They run an xtabond model and take the
coefficient of the lagged dependent variable and the capital per worker
to calculate total factor productivity as a residual.  Can anyone tell
me how to do it exactly or recommend a paper or papers I can read to
understand it.   

I have run several xtabond regressions to obtain the coefficients
mentioned above.   Then I calculate the total factor productivity (but I
am not sure  I am doing it correctly) to run OLS regressions using
variables of trade liberalization but I can't get good results.   What
is my problem?

The Sargan test and the statistics of first and second order
correlations are described in the xtabond regression in Stata, which
other test do I have to consider?

I hope anyone can help me, it is really urgent!!!!1

-----Original Message-----
From: [email protected]
[mailto:[email protected]] On Behalf Of Michael S.
Sent: 05 August 2004 17:19
To: [email protected]
Subject: Re: st: RE: log files

On Aug 5, 2004, at 11:32 AM, Nick Cox wrote:

> There are ways of creating files without
> using logs, but better advice would depend
> on knowing more about what you are doing.

	I have been wondering if there might be a way to only show
results and text explicitly displayed in the log file (or in the
Results window in certain cases), rather than all the commands as well.
  Conceptually (I think), a -log- file with the contents of -cmdlog-
stripped out.  I haven't been able to track down any ado files that
might achieve that goal....

On Aug 5, 2004, at 11:08 AM, Owens, Douglas Hamilton wrote:

> When I do this I tend to write a do-file like
> qui {
> log using x.log, replace
> noi di  "blah blah , `blah'"
> log close
> }

	... but this clever trick seems to accomplish more or less what
I had
in mind.  I never would have thought of it myself.  Thanks!

                                         -- Mike

*   For searches and help try:

*   For searches and help try:

© Copyright 1996–2024 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   What's new   |   Site index