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]
Re: st: clarity on varsoc command
From
Muhammad Anees <[email protected]>
To
[email protected]
Subject
Re: st: clarity on varsoc command
Date
Wed, 15 Feb 2012 18:02:38 +0500
One question, what is the need for selecting optimal lags for
individual variables? I assume these individual lags will do the same
what combined lags do, while apparently these are the same. So
selecting the optimal lag length for a combination of variables will
be sufficed. One option to your specific conditioning for lags might
be the ARDL, which unluckily, Stata has no such listed command. You
can fit ARDL using Microfit.
On Wed, Feb 15, 2012 at 2:03 PM, Michael Ndlovu
<[email protected]> wrote:
> Hi
>
> I am trying to create a time-series model with the optimal lags for each variable. I am using Stata version 12.
>
> My understanding of the "varsoc" command is that it gives you optimal lag choice for a set of variables. So if I have type in the command "varsoc y x z" , I will get the optimal lag choices for a model that looks like: y = cons + b1*ylag + b2* xlag + b3*zlag.
>
> My problem with this though is the assumption of the same lag period for all these variables. How do I get optimal lag choice for each variable such that the optimal amount of lags to y is not necessarily the same as x or z.
>
> Is it correct for me to isolate each variable and make the other variables exogenous
>
> i.e. varsoc y x, exog(z)
> varsoc y z, exog(x)
>
> I just need clarity on whether I am going about this the right way or whether there is another way of finding what I want.
>
> Regards
> Michael
>
>
>
> --------------------- *** Disclaimer *** ----------
> This e-mail and its contents are subject to the SA Reserve Bank's
> Disclaimer and Confidentiality Clause, which can be viewed at:
> http://www.reservebank.co.za/disclaimer
> Should you be unable to access the link provided, please send a
> blank e-mail to [email protected]
> --------------------------- *** Disclaimer *** -----
>
>
> *
> * 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/
--
Best
---------------------------
Muhammad Anees
Assistant Professor/Programme Coordinator
COMSATS Institute of Information Technology
Attock 43600, Pakistan
http://www.aneconomist.com
*
* 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/