Forecasting an estimated 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.

Forecasting an estimated model

Postby jdavis » Wed Jul 19, 2006 5:55 pm

I am trying to forecast an estimated model. The guide to dynare states that this can be done by specifying 'forecast' in the estimation command line. The following is my command line:


estimation(datafile=datapull,first_obs=50,mh_nblocks = 1,nobs=200,mode_compute=4,mh_replic=0,mode_check,forecast=40);

and the output for structure oo_ is:

oo_ =

posterior_mode: [1x1 struct]
posterior_std: [1x1 struct]
MarginalDensity: [1x1 struct]
SmoothedVariables: [1x1 struct]
FilteredVariables: [1x1 struct]
SmoothedShocks: [1x1 struct]

The substructure 'forecast' should be in oo_ but it isn't. Can you tell me how to correct the syntax to get the forecasting option to work? If it can't be done from the estimation command line then can it be done some other way?

Thanks in advance
jdavis
 
Posts: 5
Joined: Wed Jul 05, 2006 11:17 pm
Location: Evanston

Postby MichelJuillard » Sun Jul 23, 2006 6:10 pm

Forecast is available as a field in oo_ in the snapshot version of Dynare version 3

Best

Michel
MichelJuillard
 
Posts: 680
Joined: Thu Nov 18, 2004 10:51 am

Postby jdavis » Thu Aug 03, 2006 12:17 am

I downloaded the daily snapshot version of dynare and tried to forecast as was suggested above. The option still isn't working for me (it doesn't appear in the field oo_). What is the correct syntax for forecasting from an estimated model?

Thanks in advance,
Josh
jdavis
 
Posts: 5
Joined: Wed Jul 05, 2006 11:17 pm
Location: Evanston

Postby MichelJuillard » Thu Aug 03, 2006 6:58 am

I didn't see it at first: you need to run Metropolis iterations. This is a deficiancy, but currently Dynare has no provision to forecast out of the posterior mode (maximum likelihood).

Best

Michel
MichelJuillard
 
Posts: 680
Joined: Thu Nov 18, 2004 10:51 am


Return to Dynare help

Who is online

Users browsing this forum: Google [Bot] and 10 guests