Questions on impulse responses with partcular shocks

This forum is closed. You can read the posts but cannot write. We have migrated the forum to a new location where you will have to reset your password.
Forum rules
This forum is closed. You can read the posts but cannot write. We have migrated the forum to a new location (https://forum.dynare.org) where you will have to reset your password.

Questions on impulse responses with partcular shocks

Postby HappyWorld » Mon May 26, 2008 2:52 am

Hi.


I'm wondering if we can do impulse response analysis with a partcular shock, i.e, a non-i.i.d shock;


Glenn.
Last edited by HappyWorld on Wed Jun 04, 2008 10:54 am, edited 1 time in total.
HappyWorld
 
Posts: 4
Joined: Wed Apr 26, 2006 6:40 pm

Re: Questions on impulse responses with partcular shocks

Postby StephaneAdjemian » Mon May 26, 2008 10:56 am

Hi Glenn

A stochastic shock with non zero mean and/or a skewed distribution can be iid.

You can implement a non zero mean shock in Dynare. The problem is that this will eventually shift the steady state of the model. Dynare will approximate the model around the new steady state, ie after the shock. So the approximation may not be good if the mean is too far from zero. You can find the algebra of this in michel's slides [pdf]. You have to declare this kind of shock with the command varexo_det in the preamble of your mod file (see the manual and I think that you can also find some posts on the forum about this issue).

There is nothing in Dynare to handle the skewness thing. Dynare assumes that the shocks are gaussian. But nothing prevents you from considering arbitrary nonlinear transformations of the (gaussian) shocks.

Best,
Stéphane.
Stéphane Adjemian
Université du Maine, GAINS and DynareTeam
https://stepan.adjemian.eu
StephaneAdjemian
 
Posts: 429
Joined: Wed Jan 05, 2005 4:24 pm
Location: Paris, France.


Return to Dynare help

Who is online

Users browsing this forum: No registered users and 7 guests