Dealing with composite parameters during estimation


I have read “A Guide to Specifying Observation Equations for the Estimation of DSGE Models,” and I am now trying to apply the methods in this paper.
I wish to focus on the beta parameter first to get an understand of the process.

I have three questions:

  1. What is the best way to define a composite parameter when the beta is contain in the in the parameter.
    Do I define the composite parameter as a local variable in the model? For example

#local_beta = beta;

#lambda_home1 = ((1 - alpha2 + alpha2*(1 - comOpenness) + alpha1comOpenness + (alpha1 + alpha2)comOpenness)
* (1 - theta)
(1 - beta
theta))/ (1 - alpha2 + alpha2*(1 - comOpenness) + alpha1comOpenness
+ (alpha1 + alpha2)comOpenness + (-alpha2 + alpha2(1 - comOpenness) + alpha1
+ (alpha1 + alpha2)comOpenness) epsilon + theta);

ppi_os = local_betappi_os(+1) + lambda_home1mc_os;

  1. I was going along the direction of question 1 in my dynare code, but I get this error. How do I resolve this error ?

RROR: gc_ov2.mod: line 297, cols 23-28: Variable alpha2 not allowed inside model declaration. Its scope is only outside model.

  1. I am also having an issue with the likelihood function, see below. The data that I am using in the excel has the following transformation.

gdp_obs -> the cycle data of ----> hpFilter ( Log ( Y_data/ N_data))

gdp_obs is stationary …

How do resolve this error.

Warning: Matrix is close to singular or badly scaled. Results may be inaccurate. RCOND = 1.025731e-17.

In lyapunov_symm at 162
In dsge_likelihood at 374
In initial_estimation_checks at 47
In dynare_estimation_1 at 179
In dynare_estimation at 89
In gc_ov2 at 344
In dynare at 180
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):

Any help would greatly be appreciate it and thank you in advance.

gc_ov2.mod (20.5 KB)

Data File

Data File try2 (10.8 KB)

  1. If something is an independent parameter, define it as a parameter. If something is a function of other paramters, use model-local variables
  2. Every term used within the model block must be defined as either a variable or parameter or model-local variable. alpha2 is used within the block, but it has not been defined as a parameter.
  3. As discussed at [Dynare Estimation: help) the Gali/Monacelli model has unit roots in its basic form and requires the use of the diffuse_filteroption
  4. If you read my Guide, you should know that you are not supposed to use a two-sided HP_filter.