[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
st: Re: "recursive var"
What you are describing is not a VAR; it is a system of simuitaneous
equations. A VAR is just what it says: an autoregression of each
variable on the PAST values of itself and the other variables in the
VAR. Once you have a current value of any of those variables on the
RHS, you can no longer use OLS to estimate the equation. A VAR can be
estimated with equation-by-equation OLS. What you describe requires
instrumental variables techniques. If you want to estimate the entire
system, use reg3 (three-stage least squares).
Kit Baum, Boston College Economics
On Aug 27, 2005, at 2:33 AM, statalist-digest wrote:
I am trying to run a recursive VAR (vector autoregression) in which
equation(s) of the VAR system contains the current value of other
variable(s) , not just past values of the variables.
I wonder if Stata allows for including some of the current values of
Anyone who is familiar with VAR in Stata, please reply.
* For searches and help try: