Dear, Pfeifer,
What is better based on the estimation of the model parameters - when the number of shocks is equal to the number of observed variables or when the number of shocks exceeds the number of observed variables?
Thank you,
Leonid.
There is no general answer to that. Usually, the number of shocks is determined by the model. If you have more data/observables to estimate the model, that is typically a good thing. But sometimes additional observables introduce problems.