Bayesian steady state measurement error

[mbbr]

Hi everyone,

I am running model of Uribe. In simulation, I obtain the same results with Uribe. But estimation does not work even if I use the same priors with the paper and mode-compute-6. The problem may be related to measurement errors equation. But i dont know how to deal with this. Estimation works when i am estimating 16 parameters. But if i include parameter gd and estimate 17 paramaters, it fails. It gives me this results:

Configuring Dynare ...
[mex] Generalized QZ.
[mex] Sylvester equation solution.
[mex] Kronecker products.
[mex] Sparse kronecker products.
[mex] Local state space iteration (second order).
[mex] Bytecode evaluation.
[mex] k-order perturbation solver.
[mex] k-order solution simulation.
[mex] Quasi Monte-Carlo sequence (Sobol).
[mex] Markov Switching SBVAR.

Starting Dynare (version 4.3.1).
Starting preprocessing of the model file ...
Found 23 equation(s).
Evaluating expressions...done
Computing static model derivatives:
- order 1
Computing dynamic model derivatives:
- order 1
Processing outputs ...done
Preprocessing completed.
Starting MATLAB/Octave computing.


STEADY-STATE RESULTS:

c 0.150095
h 0.179761
lamda 275.756
a 1
g 1.01
k 0.292417
d 0.007
i 0.0396226
r 0.105919
y 0.211472
k_over_gh 1.61059
v 1
s 0.0211472
mu 1
gy 1.01
gc 1.01
gi 1.01
tb 0.000607129
tby 0.00287096
gy_obs 0.00995033
gc_obs 0.00995033
gi_obs 0.00995033
tby_obs 0.00287096
Loading 105 observations from arj_data.m


SOLVE: maxit has been reached
Warning: File 'mh_scale_fname' not found.
> In dynare_estimation_1 at 119
In dynare_estimation at 70
In uribefinansesty at 327
In dynare at 120

SOLVE: maxit has been reached

SOLVE: maxit has been reached
Error in computing likelihood for initial parameter values
Error using print_info (line 57)
Impossible to find the steady state. Either the model doesn't have a unique
steady state of the guess values are too far from the solution

Error in initial_estimation_checks (line 69)
print_info(info, DynareOptions.noprint)

Error in dynare_estimation_1 (line 147)
oo_ =
initial_estimation_checks(objective_function,xparam1,dataset_,M_,estim_params_,options_,bayestopt_,oo_);

Error in dynare_estimation (line 70)
dynare_estimation_1(var_list,dname);

Error in uribefinansesty (line 327)
dynare_estimation(var_list_);

Error in dynare (line 120)
evalin('base',fname) ;


Another question is: i am making first order approximation and working with nonlinear model. ı did not loglinearize the model. Why do variables dynare names as smoothed variables take negative values?


I will really appreaciate your help. Thanks!

[jpfeifer]

You have a problem with steady state computation/updating: see also http://www.dynare.org/phpBB3/viewtopic.php?f=1&t=4148

[mbbr]

You have a problem with steady state computation/updating: see also http://www.dynare.org/phpBB3/viewtopic.php?f=1&t=4148

Thank you for your suggestion. I attached my codes. Before model blocks I defined 10 parameters which depend on parameter gd. If I understand correctly in estimation i need to change these parameters but they dont. To update parameters depending on gd i need to write them in model block or write a steady state file. Am ı right? Could you send me your steady state file? Which one is better in my case writing in model block or using steady state file?

[mbbr]

this is my data.