identification problem

[marco_dp]

Dear all,

I have a problem with Dynare 4.3.3. When I run identification analysis I receive this error:

Code: Select all

==== Identification analysis ====
 
Testing prior mean
??? Attempted to access x(2,4); index out of bounds because size(x)=[1,61].

Error in ==> igem_gsa_dynamic at 236
rhs
=y(47)*params(90)*params(113)+y(68)*params(90)*params(113)-T1972*y(86)-params(83)*params(90)*params(6)*T2018*(y(101)-y(62))/params(85)/T1969/0.2e1+y(93)*T2018*params(90)*params(6)*params(83)/para
Error in ==> identification_analysis at 77
    [residual, g1 ] = feval([M_.fname,'_dynamic'],yy0, ...

Error in ==> dynare_identification at 272
    [idehess_point, idemoments_point, idemodel_point, idelre_point,
    derivatives_info_point, info] = ...

Error in ==> igem_gsa at 1215
dynare_identification(options_ident);

Error in ==> dynare at 120
evalin('base',fname) ;

If I run sensitivity analysis it works fine, as well the bayesian estimation, but I am not able to correctly perform identification.
Can please someone help me?
btw: I work for an institution and I am not allowed to post the mod file...
thanks!!!

[jpfeifer]

Please try 4.4 and report back.

[marco_dp]

Hi jpfeifer, thanks for the answer.
Unfortunately also with 4.4.0 version I got the same error.
I am using a model in logdev (using command model(linear)) with 3 shocks and 3 observables in order to avoid stochastic singularity.
I tried also to perform estimation by using the command dynare_sensitivity(identification=1,morris=2), but I got the error anyway.

thanks for the attention