# Putting stationary variables through Johansen procedure

Is it okay to feed $I(0)$ variables into the Johansen procedure? I've read three sources that seem to state that this is not what you're supposed to do. However, whenever I've done this, I notice that $\Pi$ is full rank and so it leads me to a VAR and therefore I don't see any problem with this.

-

Having I(0) variables is not a theoretical issue. Please see pp 5-6 Hjalmarsson and Österholm (2007) on this.