Variance is NAN or zero

[curry]

GH3.mod (4.1 KB)
GH3_ss.m (1.8 KB)
GH3_steadystate.m (1.5 KB)
param_GH.m (837 Bytes)
Dear professor,
I am doing a two sector model with banks. The model could run now.However, when I want to use the variance of some variables, I found that the var in “oo” block is NAN or 0, I don’t know why, could you help me to solve it.Thanks.

[jpfeifer]

See

NaN AND inf in my steady state

All of this is explained by the presence of a unit root. In this case your IRFs will have permanent effects and the unconditional second moments for the non-stationary variables do not exist, i.e. are NaN. Check whether the unit root is a feature of your model. Search the forum for more on this. There is no universal solution.

[curry]

Professor, I have checked the question on the forum. However, I don’t know where the problem of unit root comes from. I couldn’t find the problem, could you help to have a look at the code and solve the problem, Thanks.

[jpfeifer]

You may have to start from a simpler model.

[curry]

whether the unit root problem is correlated with the collinear problem? The Model -diagnosis tells me that the model has collinear problem.

[jpfeifer]

Yes, unit roots show up as a collinearity in the static Jacobian. model_diagnostics indicates the equations and variables presumably involved. But those are still too many in your model to pinpoint the issue exactly. Hence my suggestion to simplify.