Help to identify the problem with the code

[jpfeifer]

1. See

B-K conditions are not satisfied but The rank condition is verified

Your model has a unit root. You need to use diffuse_filter in the estimation-command

2. Similarly,

Is there a limit for mh_jscale?

You are not handling parameter dependence correctly. You need to fix this and then check identification.

Use model-local variables, i.e. the ones with the pound operator.