Bayseian estimation: dynare_estimation_init:: The steady state at the initial parameters cannot be computed

Estimation ML/Bayesian estimation
1

Dear all,
I receive the error message, when doing a bayseian estimation.
"dynare_estimation_init:: The steady state at the initial parameters cannot be computed.
错误使用 print_info (line 32)
The steadystate file did not compute the steady state

出错 dynare_estimation_init (line 607)
print_info(info, 0, options_);

出错 dynare_estimation_1 (line 112)
dynare_estimation_init(var_list_, dname, [], M_, options_, oo_, estim_params_, bayestopt_);

出错 dynare_estimation (line 105)
dynare_estimation_1(var_list,dname);

出错 Baseline_Ramsey0808.driver (line 440)
oo_recursive_=dynare_estimation(var_list_);

出错 dynare (line 293)
evalin(‘base’,[fname ‘.driver’]) ; "
My code and data is attached below.
Baseline_Ramsey0808.mod (9.1 KB)
China_realdata.xlsx (14.2 KB)
Plus, this model runs without Bayseian estimation, so I cannot figure out where is the problem.
Any help is appreciated, thank you in advance!

2

That’s because you decreased the tolerance of the steady state computation. But putting steady clearly shows that there is a residual in the steady state equation for marginal costs. Are you sure they are e.g. independent of the taxes?

3

Dear professor jpfeifer,
Thank you so much for the enlightment! I guess maybe the expression of marginal cost is not appropriate. Should I change the form of NKPC curve? or the form of expression of the steady-state of marginal cost? Many much thanks!
Best reguard
Haruka

4

You are the only one who can know the answer. If your NKPC is correct based on your model, then obviously the steady state equation is wrong.

1 Like
5

Dear professor jpfeifer,
Thank you again for the help! I change the expression as well as parameter of NKPC, and it works finally!
Best reguard
Haruka