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: DOLS Estimator and VEC Beta estimate


From   "kknight09" <[email protected]>
To   <[email protected]>
Subject   st: DOLS Estimator and VEC Beta estimate
Date   Sat, 20 Mar 2010 17:33:03 +0400

Dear Statalisters

My question pertains to the DOLS Procedure.

I need to find the relationship between variables (for a time series analysis), which are of a causal nature. I have worked on a VECM, since my variables are I(1) and I also have cointegrating relationships. I had no problem in estimating the short run causality using the Wald Test (via the -test- command).

The long run causality is giving me a harsh time.
I came across the DOLS procedure and a command -ivreg2- (I own Stata9).
While using -ivreg2-, I get the coefficient and the p-value for z.
The coefficient seemingly relates the long run relationship of the independent variables towards the dependent one. But does the beta coefficient from the -vec- estimation give the long run relationship as well?

If this is the case, I am getting two different results. All of my variables' beta estimate from the VEC are significant, while this is not the case with the DOLS estimator. Is this normal? Could anyone please give me an example of how to use the -ivreg2- command and a possible interpretation of the result, had I wrongly interpreted mine??

By each time changing the dependent variable, can the coefficient be used to relate causality(long run) between the different variables?

Could anyone please help me out. It's really urgent...
Thank you very much

Looking forward to hear from you soon...

Kind Regards
Ken
*
*   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