For any interested users, I have written an estimator that handles
Pooled Mean Group estimation a la Pesaran et al. (Refer to JASA or
http://econpapers.repec.org/paper/ednesedps/16.htm for more info.)
In brief, Pesaran's method allows for a common cointegrating vector and
heterogeneous short-run dynamics. My code command, xtpmg, will estimate
these types of models.
I have a working paper currently being reviewed that details the
methodology.
If anyone is interested in the code and/or paper, feel free to contact
me.
-Ed Blackburne
On Wed, 2005-11-30 at 13:31 -0500, Salvati, Jean wrote:
> > -----Original Message-----
> > From: [email protected]
> > [mailto:[email protected]] On Behalf Of
> > Christoph Birkel
> > Sent: Wednesday, November 30, 2005 12:36 PM
> > To: [email protected]
> > Subject: WG: st: RE: RE: RE: Error Correction Model
> >
> > Jean,
> >
> > does your Kao&Chiang-Panel-DOLS ado implement the
> > non-parametric correction for heterogenous panels?
>
> Not yet, I'm afraid. It was planned, but I don't use these estimators very often and I never got around to doing it.
>
> I'll try to work on this.
>
> Jean
>
> > ----- Originalnachricht -----
> > Von: "Salvati, Jean" <[email protected]>
> > Datum: Mittwoch, November 30, 2005 16:35
> > Betreff: st: RE: RE: RE: Error Correction Model
> >
> > > Mariano,
> > >
> > > It seems to me that you are referring to something like the DOLS
> > > estimators of Stock and Watson (1993) and (for panel data) Kao and
> > > Chiang (1998). Is that correct?
> > >
> > > I have ado files for these estimators, but they may need
> > more testing
> > > and polishing. The ado for the Stock and Watson estimator
> > is based on
> > > a RATS program. The ado for the Kao and Chiang estimator is
> > based on
> > > these authors' Gauss program. Other than that, I don't know
> > of any ado
> > > for these estimators.
> > >
> > > I'm curious: how exactly do you proceed in EViews?
> > >
> > > Jean Salvati
> > >
> > > References:
> > >
> > > Kao, Chihwa and Min-Hsien Chiang (1998), "On the estimation and
> > > inference of a cointegrated regression in panel data",
> > Working Paper,
> > > Syracuse University.
> > >
> > > Stock, James and Mark Watson (1993), "A simple estimator of
> > > cointegrating vectors in higher order integrated systems",
> > > Econometrica, July.
> > >
> > >
> > > > -----Original Message-----
> > > > From: [email protected]
> > > > [mailto:[email protected]] On Behalf
> > Of Mariano
> > > > Alvarez
> > > > Sent: Wednesday, November 30, 2005 10:18 AM
> > > > To: [email protected]
> > > > Subject: st: RE: RE: Error Correction Model
> > > >
> > > > Dear Al,
> > > > Mi intention is to find a command that allow me to run an Error
> > > > Correction Model, like E-views. With an ECM I mean a
> > model which the
> > > > dependent variable consists of first difference of y, and the RHV
> > > > consist of lags of the dependent variable and lags of
> > other variable
> > > > x (which we believe it´s cointegrated with y), and a
> > component that
> > > > consist of the residuals from the regression of y to x. E-views
> > > > allows me to specificy the endogenous variable. I wonder
> > if there is
> > > > a similar command in Stata that allow me to run this kind
> > of model.
> > > > Thanks
> > > >
> > > > Mariano
> > > >
> > > > -----Original Message-----
> > > > From: [email protected]
> > > > [mailto:[email protected]] On Behalf
> > Of FEIVESON,
> > > > ALAN H.
> > > > (AL) (JSC-SK311) (NASA)
> > > > Sent: Miércoles, 30 de Noviembre de 2005 12:02 p.m.
> > > > To: '[email protected]'
> > > > Subject: st: RE: Error Correction Model
> > > >
> > > > Mariano - You have to be more specific - what exactly do
> > you mean by
> > > > an "error correction model" ?
> > > >
> > > > Al Feiveson
> > > >
> > > > -----Original Message-----
> > > > From: [email protected]
> > > > [mailto:[email protected]] On Behalf
> > Of Mariano
> > > > Alvarez
> > > > Sent: Wednesday, November 30, 2005 8:21 AM
> > > > To: [email protected]
> > > > Subject: st: Error Correction Model
> > > >
> > > > Hi,
> > > >
> > > > Does anyone know how to estimate in Stata an Error
> > Correction Model?
> > > > I wonder if there is a Stata command in order to estimate
> > the model.
> > > > Thanks in advance,
> > > >
> > > >
> > > > Mariano
> > > >
> > > >
> > > > *
> > > > * 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/
> > > >
> > > >
> > > >
> > > > *
> > > > * 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/
> > >
> >
> > *
> > * 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/
*
* 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/
