permanent shock in a stochastic model

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.

permanent shock in a stochastic model

Postby mer » Sun Jun 19, 2011 8:25 pm

I am a new user. I was wondering whether dynare can deal with permanent (technology) shocks in a stochastic model. Any help will be much appreciated!
mer
 
Posts: 2
Joined: Fri Jun 17, 2011 8:00 pm

Re: permanent shock in a stochastic model

Postby jpfeifer » Mon Jun 20, 2011 8:07 am

Yes, it can. See for example the attached Dynare example (taken from the examples and changed to run in the most current Dynare version), where y_obs and p_obs are non-stationary.
Attachments
fsdat.m
Data file. May have to be
(4.52 KiB) Downloaded 327 times
fs2000ns_steadystate.m
Steady state file
(1004 Bytes) Downloaded 283 times
fs2000ns.mod
Mod-file
(2.76 KiB) Downloaded 634 times
------------
Johannes Pfeifer
University of Cologne
https://sites.google.com/site/pfeiferecon/
jpfeifer
 
Posts: 6940
Joined: Sun Feb 21, 2010 4:02 pm
Location: Cologne, Germany

Re: permanent shock in a stochastic model

Postby mer » Mon Jun 20, 2011 10:00 pm

That's awesome, many many thanks!
mer
 
Posts: 2
Joined: Fri Jun 17, 2011 8:00 pm

Re: permanent shock in a stochastic model

Postby yangv007 » Tue Feb 28, 2012 8:27 am

i still cant find the permanent shock in his attach, isnt he giving a estimation but not a solution ???
yangv007
 
Posts: 6
Joined: Thu Oct 13, 2011 10:52 am

Re: permanent shock in a stochastic model

Postby jpfeifer » Tue Feb 28, 2012 9:59 pm

If you have a process with a unit root like
Code: Select all
x=x(-1)+epsilon;

where epsilon is a stochastic shock process, any shock epsilon will be permanent. However, the most common way to implement this into Dynare is to stationarize the model by detrending it, i.e. differencing the system. In this case, you will end up with
Code: Select all
dx=epsilon;

This is similar to the dA in the attached mod-file. However, you might try to directly use a non-stationary shock process like the first one.
------------
Johannes Pfeifer
University of Cologne
https://sites.google.com/site/pfeiferecon/
jpfeifer
 
Posts: 6940
Joined: Sun Feb 21, 2010 4:02 pm
Location: Cologne, Germany


Return to Dynare help

Who is online

Users browsing this forum: No registered users and 11 guests