Probem with MLE estimation with 2nd order(particle filter)

[skchoi]

Dear all,

I am currently trying to estimate small open economy model based on Adolfson et al.(2005) with uncertainty shock.
Problem is that the model is just working when I do stochastic simulation such that "stoch_simul(order=3, pruning, irf=20) Y C X"
but in estimation with unstable dynare version(2017-01-12), I got following message and I have no idea what to do.

///////////////////////////////////////////////////////////////////////////////////////////////////

choose one of the following options:

[1] Consider all the endogenous variables.
[2] Consider all the observed endogenous variables.
[3] Stop Dynare and change the mod file.

options [default is 1] = 1

Estimation using a non linear filter!

Error in computing likelihood for initial parameter values

ESTIMATION_CHECKS: There was an error in computing the likelihood for initial parameter values.
ESTIMATION_CHECKS: If this is not a problem with the setting of options (check the error message below),
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):

Error using print_info (line 42)
Blanchard Kahn conditions are not satisfied: no stable equilibrium
Error in print_info (line 42)
error(['Blanchard Kahn conditions are not satisfied: no stable' ...
Error in initial_estimation_checks (line 169)
print_info(info, DynareOptions.noprint, DynareOptions)
Error in dynare_estimation_1 (line 149)
oo_ =
initial_estimation_checks(objective_function,xparam1,dataset_,dataset_info,M_,estim_params_,options_,bayestopt_,bounds,oo_);
Error in dynare_estimation (line 105)
dynare_estimation_1(var_list,dname);
Error in uncertainty_posting (line 1070)
oo_recursive_=dynare_estimation(var_list_);
Error in dynare (line 223)
evalin('base',fname) ;

////////////////////////////////////////////////////////////////////////////////////////////////

Also, with dynare version 4.4.3, I got this message

/////////////////////////////////////////////////////////////////////////////////////////////////

Choose one of the following options:

[1] Consider all the endogenous variables.
[2] Consider all the observed endogenous variables.
[3] Stop Dynare and change the mod file.

options [default is 1] = 1


Estimation using a non linear filter!

Loading 66 observations from dataforuncertainty2.xlsx

Initial value of the log posterior (or likelihood): -100000000
n=35: (7,14)-CMA-ES(w=[36 24 16 11 7 4 1]%, mu_eff=4.3) on function non_linear_dsge_likelihood
reduced_rank_cholesky:: Input matrix is not semidefinite positive!

////////////////////////////////////////////////////////////////////////////////////////

and matlab says "busy" for a long time.

Pleas let me know what is a problem and which dynare version should I use.

[jpfeifer]

The model has a unit root. You can work around the issue in the unstable version using

Code: Select all

diffuse_filter

which disable the respective check. Note that given the size of your model, this estimation will run a really long time.