Bookmark and Share

Notice: On April 23, 2014, Statalist moved from an email list to a forum, based at statalist.org.


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

st: RE: RE: RE: RE: RE: VEC command and aconstraints option


From   DE SOUZA Eric <[email protected]>
To   "[email protected]" <[email protected]>
Subject   st: RE: RE: RE: RE: RE: VEC command and aconstraints option
Date   Fri, 27 May 2011 17:12:44 +0200

It does make sense to separate the estimation of the short run dynamics from the cointegration relations. Too long to explain here. And I have to run.

Estimation by OLS of the cointegratiing relations is not to be recommended even in a single equation framework. The resulting estimates are known to be highly biased even for relatively large samples.

Eric

-----Original Message-----
From: [email protected] [mailto:[email protected]] On Behalf Of Kevin Amess
Sent: 27 May 2011 16:42
To: [email protected]
Subject: st: RE: RE: RE: RE: VEC command and aconstraints option

Thanks Eric. This will allow me to estimate the structural model I want to estimate.

You wrote: " If this is what you want , then you have to save the ce's with -predict- and use -var- . This is straightforward to implement, but does it make sense to save the ce's after the unrestricted -vec- model given that the presence of some variables in some short-run equations make no economic sense, which is why I want to place restrictions on some coefficients?

I was also wondering if another solution might be to estimate my cointegrating equation by OLS, save the residuals and estimate a structural model using -3sls-. Of course in this case I will not have the range of post estimation commands that -var- provides.

Thanks.


-----Original Message-----
From: [email protected] [mailto:[email protected]] On Behalf Of DE SOUZA Eric
Sent: 25 May 2011 10:32
To: [email protected]
Subject: st: RE: RE: RE: VEC command and aconstraints option

-vec- does not allow you to omit short run dynamics variables. If this is what you want , then you have to save the ce's with -predict- and use -var- .

If you want to omit a variable from the cointegration relation that is a restriction on the beta matrix.

To continue the example:

var dmp dy ddp dr, lags(1) exog(L.ce3 L.ce4) dfk constraints(11/14)

Eric de Souza
College of Europe
Brugge (Bruges), Belgium
http://www.coleurope.eu


-----Original Message-----
From: [email protected] [mailto:[email protected]] On Behalf Of Kevin Amess
Sent: 25 May 2011 10:59
To: [email protected]
Subject: st: RE: RE: VEC command and aconstraints option

Dear Eric,

Thanks for the advice, but I am looking for something a little different. If we take constraint 7, all the variables in equation D_y are omitted. However, I would like to omit just one of the variables in that equation. Is this possible?

Thanks
Kevin.

-----Original Message-----
From: [email protected] [mailto:[email protected]] On Behalf Of DE SOUZA Eric
Sent: 24 May 2011 17:07
To: [email protected]
Subject: st: RE: VEC command and aconstraints option

This is because -aconstraints- puts a restriction on the alpha matrix, whereas your constraint does not concern the alpha matrix.
Here is an example of constraints  in the -vec- command:

* IMPOSE RESTRICTIONS ON BETA
constraint 1 [_ce1]mp = 1
constraint 2 [_ce1]y = -1
constraint 3 [_ce1]dp = [_ce1]r
constraint 4 [_ce1]_trend = 0
constraint 5 [_ce2]mp = 0
constraint 6 [_ce2]y = 1

* IMPOSE CONSTRAINTS ON ALPHA
constraint 7 [D_y]L._ce1 = 0
constraint 8 [D_dp]L._ce1 = 0
constraint 9 [D_r]L._ce1 = 0
constraint 10 [D_mp]L._ce2 = 0

* RESTRICTED VECTOR ERROR CORRECTION MODEL vec mp y dp r, lags(2) rank(2) alpha trend(rtrend) aconstraints(7/10) bconstraints(1/6)


Eric de Souza
College of Europe
Brugge (Bruges), Belgium
http://www.coleurope.eu




-----Original Message-----
From: [email protected] [mailto:[email protected]] On Behalf Of Kevin Amess
Sent: 24 May 2011 16:34
To: [email protected]
Subject: st: VEC command and aconstraints option

Hello,

I am having a problem with placing constraints on adjustment parameters in a VECM model.

When I run:
constraint 1 [D_leqlibor]LD.llbovalue_real=0 vec llbovalue_real lgfcf_bi_real lFTSEallshare leqlibor if tin(1979q1,), lags(2) aconstraints(1)

I receive the following error message:
[LD.llbovalue_real] not found
r(111);

Could anyone advise as to what I am doing wrong?

Kevin.

This message and any attachment are intended solely for the addressee and may contain confidential information. If you have received this message in error, please send it back to me, and immediately delete it.   Please do not use, copy or disclose the information contained in this message or in any attachment.  Any views or opinions expressed by the author of this email do not necessarily reflect the views of the University of Nottingham.

This message has been checked for viruses but the contents of an attachment may still contain software viruses which could damage your computer system:
you are advised to perform your own checks. Email communications with the University of Nottingham may be monitored as permitted by UK legislation.
*
*   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/

*
*   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/

*
*   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 1996–2018 StataCorp LLC   |   Terms of use   |   Privacy   |   Contact us   |   Site index