Bayesian estimation of open economy model

[padmas]

I am a new user of Dynare and this may be a very basic question. I am estimating an open economy model based on Gali and Monacelli (2005) and Justiniano and Preston (2010). I get the following error from model_diagnostics. I have checked my equations a few times and it is consistent with what has been provided. If anybody could give me more insight into my error, I would be very grateful. Thanks!

model_diagnostic: the Jacobian of the static model is singular
there is 1 colinear relationships between the variables and the equations
Colinear variables:
ner
Colinear equations
1 2 3 4 5 7 8 9 10 11 12 13 14 15 16 17 18

The presence of a singularity problem typically indicates that there is one
redundant equation entered in the model block, while another non-redundant equation
is missing. The problem often derives from Walras Law.
HW2v2.mod (7.86 KB)

[jpfeifer]

In more recent versions the message actually is:

MODEL_DIAGNOSTICS: The singularity seems to be (partly) caused by the presence of a unit root
MODEL_DIAGNOSTICS: as the absolute value of one eigenvalue is in the range of ±1e-6 to 1.
MODEL_DIAGNOSTICS: If the model is actually supposed to feature unit root behavior, such a warning is expected,
MODEL_DIAGNOSTICS: but you should nevertheless check whether there is an additional singularity problem.
MODEL_DIAGNOSTICS: The presence of a singularity problem typically indicates that there is one
MODEL_DIAGNOSTICS: redundant equation entered in the model block, while another non-redundant equation
MODEL_DIAGNOSTICS: is missing. The problem often derives from Walras Law.

The variable ner has a unit root, giving rise to the message. But this should here be nothing to worry about.

[padmas]

Thank you very much for this!

[xutt]

Dear jpfeifer:
I also encounter the same problem and very confused. So I want to ask the question that if unit root is acceptable in the simulation procession, then how can it work when doing Bayesian estimation? Because Dynare will always give the same warning as there is a unit root. Can the unit root be ignore in the Bayesian estimation?
Thanks a lot ! Expect your reply!

Tina

[jpfeifer]

That depends. A unit root per se often is not a problem for estimation. The model may still satisfy the Blanchard-Kahn conditions. The only issue is the initial state of the Kalman filter. You cannot use unconditional second moments as they will not exist. The solution is to use the diffuse Kalman filter.