Problems with identification for a SMOE (As in Gali ch. 7)

[jpfeifer]

No. It's not about a unit root. But it seems your steady state file is overwriting all parameter changes the MCMC does. Your steady state must be conditional on the estimated parameters. You cannot estimate a parameter, but then set the parameter to a different value in the steady state file.

[Oriana]

I see what you meant. I already add the following code to my steadystate file:

if isfield(M_,'param_nbr') == 1
NumberOfParameters = M_.param_nbr;
for i = 1:NumberOfParameters
paramname = deblank(M_.param_names(i,:));
eval([ paramname ' = M_.params(' int2str(i) ');']);
end
check = 0;
end

My programming skills, however, are basic and I obtained the same result as before.
Some insights about the correct code shall be really appreciated.

==== Identification analysis ====

Testing posterior mode
The number of moments with non-zero derivative is smaller than the number of parameters
Try increasing ar = 2
The number of moments with non-zero derivative is smaller than the number of parameters
Try increasing ar = 3
The number of moments with non-zero derivative is smaller than the number of parameters
Try increasing ar = 4
The number of moments with non-zero derivative is smaller than the number of parameters
Try increasing ar = 5
The number of moments with non-zero derivative is smaller than the number of parameters
Try increasing ar = 6
The number of moments with non-zero derivative is smaller than the number of parameters
Try increasing ar = 7
The number of moments with non-zero derivative is smaller than the number of parameters
Try increasing ar = 8
The number of moments with non-zero derivative is smaller than the number of parameters
Try increasing ar = 9
The number of moments with non-zero derivative is smaller than the number of parameters
Try increasing ar = 10
The number of moments with non-zero derivative is smaller than the number of parameters
up to 10 lags: check your model
Either further increase ar or reduce the list of estimated parameters
Error using identification_analysis (line 102)
IDETooManyParams

Error in dynare_identification (line 280)
[idehess_point, idemoments_point, idemodel_point, idelre_point, derivatives_info_point, info]
= ...

Error in nonlinearomega (line 1952)
dynare_identification(options_ident);

Error in dynare (line 180)
evalin('base',fname) ;

[Oriana]

Looking for answers I obtained the same error when running dynare 4.4.3 with my mode file ( nonlinearomeg_22 USA.zip ) and dynare 4.3.3 with the .mod and steady state files in annexes ( see uribe.zip folder, source viewtopic.php?f=1&t=4148).

Must I conclude that both steady state files are overwriting all parameter changes the MCMC does or it is indeed another problem?

ERROR:
==== Identification analysis ====

Testing posterior mode
The number of moments with non-zero derivative is smaller than the number of parameters
Try increasing ar = 2
The number of moments with non-zero derivative is smaller than the number of parameters
Try increasing ar = 3
The number of moments with non-zero derivative is smaller than the number of parameters
Try increasing ar = 4
The number of moments with non-zero derivative is smaller than the number of parameters
Try increasing ar = 5
The number of moments with non-zero derivative is smaller than the number of parameters
Try increasing ar = 6
The number of moments with non-zero derivative is smaller than the number of parameters
Try increasing ar = 7
The number of moments with non-zero derivative is smaller than the number of parameters
Try increasing ar = 8
The number of moments with non-zero derivative is smaller than the number of parameters
Try increasing ar = 9
The number of moments with non-zero derivative is smaller than the number of parameters
Try increasing ar = 10
The number of moments with non-zero derivative is smaller than the number of parameters
up to 10 lags: check your model
Either further increase ar or reduce the list of estimated parameters
Error using identification_analysis (line 102)
IDETooManyParams

Error in dynare_identification (line 280)
[idehess_point, idemoments_point, idemodel_point, idelre_point, derivatives_info_point, info] = ...

Error in nonlinearomega (line 1887)
dynare_identification(options_ident);

Error in dynare (line 180)
evalin('base',fname) ;

[jpfeifer]

Please follow the steady state file example in the NK_baselined.mod of the Dynare examples folder. When doing so, replace the model-local variabes (the one with the # operator) by corresponding assignments within the steady state file. After doing this, also set

Code: Select all

ar=10

in the call to estimation

[Oriana]

Thank you. I already followed the previous advice and changed the models in annexe accordingly to the NK_baselined.mod. I got the expected result with uribe model but not with the nonlinearomega. What could be wrong? I shall deeply appreciated some help in order to figure it out.

[Oriana]

Forget! I already solved it!

[jpfeifer]

What was the problem?

[Oriana]

There were two problems:
- c1omegaoc and c1omegaoy weren't deep parameters, so it didn't make sense to use priors for these parameters. I simple got rid of them in the estimated_params block.
-I also had nograph, nodiagnostic, tex as options in the estimation. Even so, I was able to see the graphs of shock decomposition due to the graph_decomp.m file but not all the others graphs.

My gratitude for all the support you gave until this moment.

[unisun]

We are still working on this. But if e only enters as a first difference, drop e and define the first difference as a new variable.

Dear Pro. Jpfeifer, has this issue been solved? I encountered the same problem when I am trying to estimate my dsge model using dynare.

[jpfeifer]

Have you tried the unstable version?