St:About DOLS

classic Classic list List threaded Threaded
5 messages Options
Reply | Threaded
Open this post in threaded view
|

St:About DOLS

Alex-38
Dear statalisters,
There are two sets of number A and B. In a DOLS  model, the Depended
variable  equal to A - B; the independent variables is A + B, when I
do the DOLS regression,would the estimated parameters be biased or
inconsistent ? If there is how can I make it up?
Best regards.
--
Alex

Nankai University
Economic Department
[hidden email]
*
*   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/
Reply | Threaded
Open this post in threaded view
|

Re: St:About DOLS

Scott Merryman
Page 6 of discusses some conditions necessary  for dynamic ols:

http://www.newyorkfed.org/research/epr/99v05n1/9904klit.pdf

See also:

http://www.stata.com/statalist/archive/2009-03/msg01009.html

Scott

On Thu, Aug 12, 2010 at 11:47 AM, Alex <[hidden email]> wrote:
> Dear statalisters,
> There are two sets of number A and B. In a DOLS  model, the Depended
> variable  equal to A - B; the independent variables is A + B, when I
> do the DOLS regression,would the estimated parameters be biased or
> inconsistent ? If there is how can I make it up?
> Best regards.
> --
> Alex

*
*   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/
Reply | Threaded
Open this post in threaded view
|

Re: St:About DOLS

wangpan110
Dear Scott, can i ask you two questions, please:

1)   the last condition is "the DOLS residuals must be significantly correlated with subsequent monthly changes in relative export prices", does that mean cov(Uit, Yit) is not zero? can i achieve this in STATA?

2) what is the equation for ECM under panel data( let's say i have 4 independent variables)?

your help is very appreciated

pan

Reply | Threaded
Open this post in threaded view
|

Re: St:About DOLS

Scott Merryman
1.  I don't know.

2.  I don't know.

I have no particular knowledge of these types of models.

I would point out that -findit panel cointegration- points to several
user written commands :


    -nharvey-: module to perform Nyblom-Harvey panel test of common stochastic
    trends


    -xtdolshm-: module to perform dynamic ordinary least squares for
    cointegrated panel data with homogeneous covariance structure


    -xtpmg-: module for estimation of nonstationary heterogeneous panels


    -xtwest-: module for testing for cointegration in heterogeneous panels


Scott


On Sat, Sep 25, 2010 at 10:17 AM, wangpan110 <[hidden email]> wrote:

> Dear Scott, can i ask you two questions, please:
>
> 1)   the last condition is "the DOLS residuals must be significantly
> correlated with subsequent monthly changes in relative export prices", does
> that mean cov(Uit, Yit) is not zero? can i achieve this in STATA?
>
> 2) what is the equation for ECM under panel data( let's say i have 4
> independent variables)?
>
> your help is very appreciated
>
> pan
>

*
*   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/
Reply | Threaded
Open this post in threaded view
|

Re: St:About DOLS

wangpan110
Thanks Scott, i am working on it

Pan