help: Sargent codes from (Practicing Dynare)

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.

help: Sargent codes from (Practicing Dynare)

Postby hbadrakhan » Thu Dec 08, 2011 7:00 pm

Dear all,
I'm trying to run Sargent's codes from (Practicing Dynare) under dynare 4.2.4 and non of the codes seem to work under it.
In running (sargent77Bayes.mod) file, i get the following error massage:

This version of Dynare cannot estimate non linearized models!
Set "order" equal to 1.

Loading 34 observations from cagan_data.mat

Error in computing likelihood for initial parameter values
??? Error using ==> print_info at 39
Blanchard Kahn conditions are not satisfied: no stable equilibrium

Error in ==> initial_estimation_checks at 101
print_info(info, options_.noprint)

Error in ==> dynare_estimation_1 at 122
initial_estimation_checks(xparam1,gend,data,data_index,number_of_observations,no_more_missing_observations);

Error in ==> dynare_estimation at 62
dynare_estimation_1(var_list,varargin{:});

Error in ==> sargent77Bayes at 121
dynare_estimation(var_list_);

Error in ==> dynare at 120
evalin('base',fname) ;

The code runs just fine under dynare 4.0.4, but does any one know how can I fix it and make it work under dynare 4.2.4? thanks alot
I am attaching the file and the data and I appreciate your help.
Attachments
Sargent 1977.rar
(1.69 KiB) Downloaded 137 times
hbadrakhan
 
Posts: 8
Joined: Sun Mar 15, 2009 5:29 pm

Re: help: Sargent codes from (Practicing Dynare)

Postby SébastienVillemot » Wed Jan 04, 2012 11:24 am

This type of error indicates an indeterminacy of the model for the parameters given as a starting value of the optimization.

The fact that the behavior changed between versions of Dynare may come from several sources: we fixed bugs since version 4.0.4, we changed the random number generators...

Try to play with the initial values given in estimated_params. You may get a valid starting point by changing values a little bit.
Sébastien Villemot
Economist at OFCE – Sciences Po
SébastienVillemot
 
Posts: 706
Joined: Fri Dec 07, 2007 2:29 pm
Location: Paris, France

Re: help: Sargent codes from (Practicing Dynare)

Postby wanghao19820707 » Sun Jan 15, 2012 6:21 am

Hi ,Hbadrakhan
when I run my mod file(not Sargent codes,just my own code) it has quite same error message as yours.Did you fix the problem yet? How did you fix it ?
Many thanks!

??? Error using ==> print_info at 39
Blanchard Kahn conditions are not satisfied: no stable equilibrium

Error in ==> initial_estimation_checks at 101
print_info(info, options_.noprint)

Error in ==> dynare_estimation_1 at 122
initial_estimation_checks(xparam1,gend,data,data_index,number_of_observations,no_more_missing_observations);

Error in ==> dynare_estimation at 62
dynare_estimation_1(var_list,varargin{:});

Error in ==> houseinvest at 227
dynare_estimation(var_list_);

Error in ==> dynare at 120
evalin('base',fname) ;
wanghao19820707
 
Posts: 19
Joined: Tue Jan 03, 2012 4:07 am


Return to Dynare help

Who is online

Users browsing this forum: No registered users and 5 guests