I’d like to know what is the best way to get the IRFs of a baysian estimated DSGE model. Should I use stoch_simul?
My model is attached, so can you help me telling where should I write the part of code that indicates the IRF?
Data_Brasil.m (7.96 KB)
dynare_code.txt (8.52 KB)
Once I tried to insert this part in the code:
stoch_simul(conditional_variance_decomposition = [1 2 4 8 12 40], relative_irf, irf=40);
But when I checked the result, it didnt make sense. For exemple, the IRF of the variable d_y (productio growth) to policy monetary shocks (eps_i) went from -120 to 20… but the values of growth in the period analysed is in the interval: -0.0390,0.0270].
I dont know if the graph is in a different scale, or just wrong.
Why don’t you use the bayesian_irf option of the estimation command?