MJDGGES returns the following error code: 32

[rockyyao]

Greetings!

I am running a loglinearized model with Dynare 4.2.2., I get the following message:

MJDGGES returns the following error code: 32

I cannot seem to find anything indicating what this code might mean. Any help would be much appreciated.

[jpfeifer]

If you use

Code: Select all

model_diagnostics(M_,options_,oo_)


you get

model_diagnostic: the Jacobian of the static model is singular
there is 2 colinear relationships between the variables and the equations
Relation 1
Colinear variables:
p
pp
p0
AUX_ENDO_LEAD_175
AUX_ENDO_LEAD_181
AUX_ENDO_LEAD_187
AUX_ENDO_LEAD_193
AUX_ENDO_LEAD_199
AUX_ENDO_LAG_6_1
AUX_ENDO_LAG_6_2
AUX_ENDO_LAG_6_3
AUX_ENDO_LAG_6_4
AUX_ENDO_LAG_6_5
AUX_ENDO_LAG_6_6
Relation 2
Colinear variables:
d_7
Relation 1
Colinear equations
1 2 3 4 5 6 7 8

Relation 2
Colinear equations
14 15 16

Hence, there still is a problem with your model setup.

[rockyyao]

I found the mistake in my code.

Thanks a lot for your help.

[grossman2000]

To rockyyao: can you share what kind of mistake(s) you found? As I also received similar error messages, I am wondering if your findings may give me some hints as well. Thanks a lot!

To jpfeifer: using your suggested command, model_diagnostics(M_,options_,oo_), I found that there is also a colinear problem with 2 variables in my model equations. What does this generally mean? Can you provide some advice on what to do next? I really appreciate in advance.

[rockyyao]

In my case, I found the parameter matrix A has a colume of zeros ( Xt+1 = A Xt + B et) , so that it has not full rank. I think colinearity means the same thing. You might check your model carefully, if possible, write out the A matrix explicitly or change parameter values to see if it has a full rank or not.

Maybe it helps...

[grossman2000]

I see. Thank you very much for your suggestion.

In my case, I found the parameter matrix A has a colume of zeros ( Xt+1 = A Xt + B et) , so that it has not full rank. I think colinearity means the same thing. You might check your model carefully, if possible, write out the A matrix explicitly or change parameter values to see if it has a full rank or not.

Maybe it helps...

[grossman2000]

I have solved this problem but got another one which says:

??? Error using ==> print_info at 39
Blanchard Kahn conditions are not satisfied: no stable equilibrium

Using command check, I got the following message:
------------------------------------------------------------------------
There are 13 eigenvalue(s) larger than 1 in modulus
for 12 forward-looking variable(s)

The rank conditions ISN'T verified!
-----------------------------------------------------------------------

Does anyone know what thse might suggest?

Thanks very much!

To rockyyao: can you share what kind of mistake(s) you found? As I also received similar error messages, I am wondering if your findings may give me some hints as well. Thanks a lot!

To jpfeifer: using your suggested command, model_diagnostics(M_,options_,oo_), I found that there is also a colinear problem with 2 variables in my model equations. What does this generally mean? Can you provide some advice on what to do next? I really appreciate in advance.

[grossman2000]

Finally solved the problem. It was caused by a couple of small typos. Thanks for everyone.

I have solved this problem but got another one which says:

??? Error using ==> print_info at 39
Blanchard Kahn conditions are not satisfied: no stable equilibrium

Using command check, I got the following message:
------------------------------------------------------------------------
There are 13 eigenvalue(s) larger than 1 in modulus
for 12 forward-looking variable(s)

The rank conditions ISN'T verified!
-----------------------------------------------------------------------

Does anyone know what thse might suggest?

Thanks very much!

To rockyyao: can you share what kind of mistake(s) you found? As I also received similar error messages, I am wondering if your findings may give me some hints as well. Thanks a lot!

To jpfeifer: using your suggested command, model_diagnostics(M_,options_,oo_), I found that there is also a colinear problem with 2 variables in my model equations. What does this generally mean? Can you provide some advice on what to do next? I really appreciate in advance.