Statalist


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

Re: RE: st: RE: VAR or VEC model


From   Robert A Yaffee <bob.yaffee@nyu.edu>
To   statalist@hsphsun2.harvard.edu
Subject   Re: RE: st: RE: VAR or VEC model
Date   Tue, 25 Aug 2009 09:55:22 -0400

Ihtesham,
    Read the literature on the Johansen trace and maximum eigenvalue
tests for vector cointegration.   You may wish to run the 

vectstable, graph

command to ascertain whether your long-run matrix is of full rank.

Then you want to run the 

vecrank 

command to apply the Johansen tests
for cointegrated vectors.   
   
     I hope this is of help.  
          Cheers,
                 Bob

    
Robert A. Yaffee, Ph.D.
Research Professor
Silver School of Social Work
New York University

Biosketch: http://homepages.nyu.edu/~ray1/Biosketch2009.pdf

CV:  http://homepages.nyu.edu/~ray1/vita.pdf

----- Original Message -----
From: Ihtesham Afzal <ihtesham_afzal@hotmail.co.uk>
Date: Tuesday, August 25, 2009 4:01 am
Subject: RE: st: RE: VAR or VEC model
To: statalist@hsphsun2.harvard.edu


> Thanks you for your reply.
> But how then do I test for cointegration between the variables in the 
> model? I was made to believe that the only way of finding 
> cointegrating verctors was by doing the -vecrank- and -vec- commands. 
> 
> So do I use the var model and then -vargranger -to test for granger causality
> and then -vec- and -vecrank- commands to test for cointegration?
> Kind Regards
> Ihtesham
> 
> ----------------------------------------
> > Date: Tue, 25 Aug 2009 00:51:48 +0100
> > Subject: Re: st: RE: VAR or VEC model
> > From: clivelists@googlemail.com
> > To: statalist@hsphsun2.harvard.edu
> >
> > Ihtesham Afzal wrote:
> >
> >> Thank you for your reply.
> >> All of the variables are integrated of the same order (i.e I(1))
> >> How do I run the granger causality test? Do I run the regression of 
> one variable on the other with appropriate lags and then do an f-test 
> to test whether these lags of the indepndent variable are equal to 
> zero? And what command tdo I use to see what lag length to use -> I 
> used -varsoc- is that right?
> >> And then do this separately for all variables?
> >
> > -help vargranger-
> >
> > --
> > Clive Nicholas
> >
> > [Please DO NOT mail me personally here, but at
> > . Please respond to contributions I make in
> > a list thread here. Thanks!]
> >
> > "My colleagues in the social sciences talk a great deal about
> > methodology. I prefer to call it style." -- Freeman J. Dyson.
> >
> > *
> > * 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/
> _________________________________________________________________
> Windows Live Messenger: Thanks for 10 great years—enjoy free winks and 
> emoticons.
> http://clk.atdmt.com/UKM/go/157562755/direct/01/
> *
> *   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/



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