Hi
I am trying to estimate a structural var of gap growth and money supply with long term restrictions. I plot the responses to the shocks for gdp level using the following code. One shock has a permanent effect on gdp level and the other (restricted to zero) will have a transitory effect.
Note that dlogrgnp is a growth rate.
Assuming that my code above is correct, how can I estimate variance decomposition for both gdp growth (dlogrgnp) and gdp level?
Thanks
I am trying to estimate a structural var of gap growth and money supply with long term restrictions. I plot the responses to the shocks for gdp level using the following code. One shock has a permanent effect on gdp level and the other (restricted to zero) will have a transitory effect.
Note that dlogrgnp is a growth rate.
Code:
matrix c=(.,0\.,.) svar dlogrgnp money, lags(1/8) lreq(c) cap irf drop ir irf set ir irf create ir, step(40) set(ir) replace use ir.irf, clear sort irfname impulse response step gen csirf=sirf by irfname impulse: replace csirf= sum(sirf) if response=="dlogrgnp" order irfname impulse response step sirf csirf save ir2.irf, replace irf set ir2.irf irf graph csirf, yline(0, lcolor(black)) noci xlabel(0(1)40) byopts (yrescale)
Thanks
