Posterior Mode v.s. Posterior Mean

[fuyangzhao]

Hi Professor，
In dynare reference manuel, it is said that

After running estimation, the parameters M_.params and the variance matrix M_.Sigma_e of the shocks are set to the mode for maximum likelihood estimation or posterior mode computation without Metropolis iterations.
After estimation with Metropolis iterations (option mh_replic > 0 or option load_mh_file set) the parameters M_.params and the variance matrix M_.Sigma_e of the shocks are set to the posterior mean.

However, I want to get the estimation output

Code: Select all

 oo_.PosteriorIRF.dsge.HPDinf/sup

where M_.params and M_.Sigma_e are set to the posterior mode ...Is that possible?

Or, is the estimation output

Code: Select all

 oo_.PosteriorIRF.dsge.HPDinf/sup

the same no matter M_.params and M_.Sigma_e are set to the posterior mode or to the posterior mean?

[jpfeifer]

The question is not well-defined.

Code: Select all

HPDinf/sup


is a "confidence band" across parameters. You cannot compute the variability of IRFS across parameters if you fix the parameters.