st: imposing a constraint on an endogenous variable when using irf createin Stata 9

[Eyal Dvir <dvir@fas.harvard.edu>]

Hi,

I am trying to find a way to impose a constraint on an endogenous 
variable when Stata computes impulse response functions using irf create.

I estimated a SVAR of 5 variables, and would like to find a way to force 
one of the variables to remain constant when the impulse response 
function is computed. This is following Sims and Zha (1996).

I tried manipulating the SVAR results: I modified e(b_var) and e(b) such 
that zeros replaced all the coefficients (respectively, lagged and 
contemporaneous) of the variable in question, using the ereturn command. 
I then created another impulse response function using irf create.
I succeeded in suppressing the variable's response to lagged values - 
the modification of e(b_var) was effective - but the contemporaneous 
response remained the same - the modification of e(b) did not have any 
effect.
This method is crude, yet I couldn't find a better way - I tried the 
statalist archives, Googling, as well as the manuals. This method also 
does not allow me to impose a constraint for some of the steps in the 
irf, but not for others.

If anyone has a piece of advice for me, I would be very grateful.

Many thanks,

Eyal Dvir
dvir@fas.harvard.edu
*
*   For searches and help try:
*   http://www.stata.com/support/faqs/res/findit.html
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/