BVAR-DSGE Estimation

[klg123]

Hello,

I estimated a DSGE model and am now amending the code to estimate a BVAR-DSGE (Del Negro and Schorfheide (2004; 2005), etc.). I am getting some error messages and cannot find detailed guidance on how to do this estimation beyond the dsge_var=. command. The problematic error seems to be

VarSampleMoments :: not enough data to initialize! Try to increase FirstObservation.

I have read the relevant papers carefully and am not sure what to do. Might someone look at my code and data for potential issues here?

Thank you!

[klg123]

Does anyone have any advice here?

[jpfeifer]

Set at least

Code: Select all

first_obs=5

[klg123]

Thank you for your response. I am still having errors. The error message reads:

ESTIMATION_CHECKS: There was an error in computing the likelihood for initial parameter values.
ESTIMATION_CHECKS: You should try using the calibrated version of the model as starting values. To do
ESTIMATION_CHECKS: this, add an empty estimated_params_init-block with use_calibration option immediately before the estimation
ESTIMATION_CHECKS: command (and after the estimated_params-block so that it does not get overwritten):

yet I have already added the empty block. I am attaching my code for further inspection. I am not sure why the parameter values would not work, as I did estimate the DSGE model without problems using the same values.

Thank you kindly.

[jpfeifer]

Note the message before that output. There is a technical condition for the dsge_var-parameter prior to be proper. You must increase dsge_var to at least 0.75 in your case.

[klg123]

I am slightly confused. In the estimation command, dsge_var is already set to 0.75. Is there someplace else where this must be represented?

[jpfeifer]

Sorry old version. It must be at least 1.48.

[klg123]

Thank you. Still, with this change, I get:

Error in computing likelihood for initial parameter values

ESTIMATION_CHECKS: There was an error in computing the likelihood for initial parameter values.
ESTIMATION_CHECKS: You should try using the calibrated version of the model as starting values. To do
ESTIMATION_CHECKS: this, add an empty estimated_params_init-block with use_calibration option immediately before the estimation
ESTIMATION_CHECKS: command (and after the estimated_params-block so that it does not get overwritten):

I am using DYNARE 4.4.2. Am I missing something?

[jpfeifer]

With

Code: Select all

dsge_var = 1.75,

it runs (although there might be another issue as Dynare warns of near singularity. If it does not run, provide the updated mod-file and datafile. Note also that the name of the data-file above does not match the one used in the mod-file.

[nmutoti]

I have just joined the forum and also new to dynare. I have been reading comments on BVAR-DSGE estimation. Could anyone have the final codes that resolved the problems?