Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down at the end of May, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

Re: st: xthtaylor by hand or using xtivreg2


From   "M.M. Kramer" <M.M.Kramer@rug.nl>
To   statalist@hsphsun2.harvard.edu
Subject   Re: st: xthtaylor by hand or using xtivreg2
Date   Thu, 10 Nov 2011 12:22:20 +0100

Dear Mark,

The xtoverid works very well, thanks a lot for your help. It now gives first stage results for all instrumented variables, and given that all variables are instrumented, I get many first stage results, including some useful statistics. My only question is whether there is an easy way to see which variable is behind the "recoded" variable that xtoverid creates (with names like: __00000J __00000M __00000P __00000S __00000V, etc). I was thinking to correlate them with the original variables to see whether something can be inferred from that, but the new variables are not kept in Stata. Do you have any suggestion for this?

Thanks,
Marc



Schaffer, Mark E wrote:
Marc,

The xtoverid update is now available (with thanks as usual to Kit Baum).
The -noi- option automatically triggers the -first- option in the
internal call to -ivreg2- so you should see everything about the
first-stage estimations.

Best wishes,
Mark

-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu [mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of M.M. Kramer
Sent: 03 November 2011 10:22
To: statalist@hsphsun2.harvard.edu
Subject: Re: st: xthtaylor by hand or using xtivreg2

Mark,

thanks a lot, I'll wait for the update.

Marc

Schaffer, Mark E wrote:
Marc,

I found the source of your first problem: the undocumented
-noisily-
option of -xtoverid- was using another option that was incompatible with displaying first-stage results.

I'll fix it and let you and the rest of the list know when
the update
is available.

Cheers,
Mark

-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of M.M. Kramer
Sent: 02 November 2011 15:06
To: statalist@hsphsun2.harvard.edu
Subject: Re: st: xthtaylor by hand or using xtivreg2

Hi Mark,

After xtoverid, noisily (I cannot find xtoverid2) I receive the following errors:
1. Unable to display summary of first-stage estimates; macro
e(first) is missing 2. xtoverid error: internal
reestimation of eqn
differs from original

And sometimes also:
Warning - endogenous variable(s) collinear with instruments
                      *:  3200  conformability error
                s_egmm():     -  function returned error
                 <istmt>:     -  function returned error

Thanks for your help.
Marc


Schaffer, Mark E wrote:
Marc,

What is the problem you encounter when using xtoverid or
xtoverid2
with the noisily option? Is it that the full first-stage results aren't displayed? I was looking at the code and it seems
that this
undocumented option should - but doesn't - trigger display of the first-stage results.

--Mark

-----Original Message-----
From: owner-statalist@hsphsun2.harvard.edu
[mailto:owner-statalist@hsphsun2.harvard.edu] On Behalf Of M.M. Kramer
Sent: 02 November 2011 09:26
To: statalist@hsphsun2.harvard.edu
Subject: Re: st: xthtaylor by hand or using xtivreg2

Dear Nick,

I am trying to estimate the impact of a self-choosen
treatment on
portfolio returns of retail investors. This self-choosen
treatment is
very likely endogenous, it does not vary over time and we
do not have
external instuments available, so Hausman-Taylor might be an appropriate estimation technique. The problem that I keep encountering is that I cannot assess the quality of the
instruments
that xthtaylor creates. I cannot see the first stage
results when
using xtoverid2 and I receive warnings on collinearity. My
idea was
to create the instruments by hand and then use 2SLS to
see what's
going on. So far, I found that xthtaylor transforms the
timevarying
exogenous variables into means, and demeaned variables and
uses some
other transformations.
My question therefore is how exactly to replicate the variable transformation of xthaylor to create the instruments by hand.

Marc

Nick Cox wrote:

Many people will sympathise to some degree here, but what
kind of help
are you expecting _which can reasonably be provided_?

1. To comment helpfully on your difficulties with
-xthtaylor- people
will surely want more detail on your problems.

2. If you seek to use -xtivreg2- (SSC), the same comment applies
there: the help is the place to start and people will
want to see
specific queries.

3. -xthtaylor- is some hundreds of lines long, so
reproducing it "by
hand" is not trivial.

Nick

On Wed, Nov 2, 2011 at 8:26 AM, M.M. Kramer
<M.M.Kramer@rug.nl> wrote:
I have been struggling for some time with the
xthtaylor command.
Especially the various error messages that occur after
some tests are hard to solve.
Does anyone have any clear instructions on how to
transform the
variables in a way that xtivreg2 can be used?  Or may be
anyone has
the syntax to replicate the output of xthtaylor by hand.
Thanks.
Marc Kramer
*
*   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/
--
Marc Kramer
University of Groningen
Faculty of Economics & Business
Department of Economics, Econometrics and Finance Room WSN
860 P.O.
Box 800 9700 AV Groningen
Tel.: 050-363.4532 / 3685

*
*   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/

--
Marc Kramer
University of Groningen
Faculty of Economics & Business
Department of Economics, Econometrics and Finance Room WSN
860 P.O.
Box 800 9700 AV Groningen
Tel.: 050-363.4532 / 3685

*
*   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/

--
Marc Kramer
University of Groningen
Faculty of Economics & Business
Department of Economics, Econometrics and Finance Room WSN 860 P.O. Box 800 9700 AV Groningen
Tel.: 050-363.4532 / 3685

*
*   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/







--
Marc Kramer
University of Groningen
Faculty of Economics & Business
Department of Economics, Econometrics and Finance
Room WSN 860
P.O. Box 800
9700 AV Groningen
Tel.: 050-363.4532 / 3685

*
*   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/


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