Problem with estimation in Dynare

Estimation ML/Bayesian estimation
1

dear all:
there are something wrong with my bayes.mod,and i don’t know how to solve it.anybody else can help me please?thanks a lot!
codes list as follows:

错误使用 dseries/extract (第 91 行)
dseries::extract: Variable y is not a member of o!

出错 dseries/subsref (第 245 行)
r = extract(o,S(1).subs{:});

出错 makedataset (第 142 行)
DynareDataset = DynareDataset{DynareOptions.varobs{:}};

出错 dynare_estimation_init (第 553 行)
[dataset_, dataset_info, newdatainterfaceflag] = makedataset(options_,
options_.dsge_var*options_.dsge_varlag, gsa_flag);

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

出错 dynare_estimation (第 105 行)
dynare_estimation_1(var_list,dname);

出错 bayes.driver (第 598 行)
oo_recursive_=dynare_estimation(var_list_);

出错 dynare (第 293 行)
evalin(‘base’,[fname ‘.driver’]) ;
bayes.mod (7.0 KB)
HP.xlsx (12.0 KB)

2

If the first column does not have a header, you need to specify the data location using xls_range

3

thanks,dear professor!I have modified the codes but another problem arises,how to solve it?

错误使用 dates/subsref (第 162 行)
dates::subsref: indices has to be a vector of positive integers less than or equal to 48!

出错 dseries/subsref (第 270 行)
r = subsref(r, S);

出错 makedataset (第 216 行)
firstobs = DynareDataset.dates(DynareOptions.first_obs);

出错 dynare_estimation_init (第 553 行)
[dataset_, dataset_info, newdatainterfaceflag] = makedataset(options_,
options_.dsge_var*options_.dsge_varlag, gsa_flag);

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

出错 dynare_estimation (第 105 行)
dynare_estimation_1(var_list,dname);

出错 bayes.driver (第 600 行)
oo_recursive_=dynare_estimation(var_list_);

出错 dynare (第 293 行)
evalin(‘base’,[fname ‘.driver’]) ;bayes.mod (7.1 KB)
HP.xlsx (12.0 KB)

4

Your dataset only has 48 observations, but you set

first_obs=101
6

really appreciate your support,dear professor!
It really works but mode_check shows that Log data density [Laplace approximation] is NaN.I have seen related reply during the forum but still don’t understand.how could i do next?thanks a lot!!
bayes.mod (7.1 KB)
HP.xlsx (12.0 KB)

7

Why is your data still trending?

8

I have processed the data.the procedure is:1.transform into real variable;2.Logarithmic;3.X13 seasonal adjustment;4.hp filter process.how to sovle the tranding problem?do you mean is there something wrong with data or codes?thank you very much!

9
  1. Your data file clearly does not contain the HP filter’s cyclical component. Did you save the trend?
10

dear professor,I have solved the data problem of trend but it still doesn’t work.how can i do next?I’m really puzzled.
bayes.mod (7.1 KB)
hpdetrend.xlsx (12.3 KB)

11

Your observation equations are wrong/non-existent. Please read Pfeifer(2013): “A Guide to Specifying Observation Equations for the Estimation of DSGE Models”

12

thanks,dear professor!