Crash during estimation with unit roots

Hi,

I am getting this error in Dynare 3 "Error in ==> dynare at 26
evalin(‘base’,fname) ;

I have checked my mod file and I think it’s correct. What am I missing?

Please provide the file

Please find attached file. Thanks for your kind response.
Dynare_Error.zip (17.8 KB)

When you run ML, you need to make sure that all parameters are properly initialized. Also, your model has a unit root and thus requires the diffuse_filter.
In the unstable version, you can use

[code]estimated_params_init(use_calibration);
end;

estimation(datafile=data_nk,first_obs=1,mode_compute=5,diffuse_filter);
[/code]

[quote=“jpfeifer”]When you run ML, you need to make sure that all parameters are properly initialized. Also, your model has a unit root and thus requires the diffuse_filter.
In the unstable version, you can use

[code]estimated_params_init(use_calibration);
end;

estimation(datafile=data_nk,first_obs=1,mode_compute=5,diffuse_filter);
[/code][/quote]

Thanks for Your kind response. This worked in the recent version of Dynare and I am happy about that but it still doesn’t work in Dynare 3. Both of these gives synatx error in Dynare 3. Since, I am dealing with some matrices I have to use Dynare 3. Kindly help me with Dynare 3.

In that case, you need to provide the initial parameter values explicitly and use

[quote=“jpfeifer”]In that case, you need to provide the initial parameter values explicitly and use

lik_init=2

Thanks for your kind response. I tried with what you suggested but, I am getting same error. I have attached the mod file. I added estimated_params_init and estimated_params_bounds block separately to check whether that makes it work. But it is still not working.
Estimation1.mod (3.08 KB)

I was able to run the attached files in Dynare 3.6.4
Dynare_v3_mod.zip (3.44 KB)

Thanks for your kind response. It worked for me as well. I am facing the same problem with the attached mod file also. It would be great if you can tell me the probable reasons for this error so that I can try to figure out on my own. I would be obliged if you can help me with the attached mod file. I am estimating the model using same data.
Estimate_Imp_Tech_Inf.mod (3.82 KB)

Please always provide the error message you are facing. In this case, the problem comes from Dynare 3 not knowing block comments with /*. You must use

// //This file estimates the New Keynesian model As in Abhishek Kumar (2017): // This implementation was written by Abhishek Kumar. //@ Abhishek Kumar //

I will keep that in mind. Thanks for your kind response. It worked.

Hi,

I am facing an error with Identification command in dynare. I check the Blanchard Kahn condition before estimation and it says rank condition satisfied. But when I go for Identification it says "Parameter error:
The model does not solve for ML_Starting_value with error code info = 3

info==3 %! Blanchard & Kahn conditions are not satisfied: no stable equilibrium."

Can you please let me know the probable reason for this and how to approach this problem.

In Dynare 4.5, you need to add

to the identification command

[quote=“jpfeifer”]In Dynare 4.5, you need to add

to the identification command[/quote]

Thanks for your kind response. It worked.