How to deal with the stability issue of PVAR(p) model?

I am using panelvar package to estimate panel VAR model.

It is a common procedure checking the stability of the panel VAR model.

In the literature, they just report that all eigenvalues are less than one. But the question is that if there are some eigenvalues larger than one, how to make the model stable?

If all variables in the model are stationary, and the stability condition of panel VAR is still not satisfied, what should I do to make all eigenvalues less than one?

Thanks.

This topic was automatically closed 21 days after the last reply. New replies are no longer allowed.

If you have a query related to it or one of the replies, start a new topic and refer back with a link.