nonlinear state variable

[ggyyakl]

Hi there

I am trying to construct a state space model to derive an unobserved variable, I have prior belief that this state variable is non-linearly related to the signal variable
. I understand Eviews 7 states that their relationship must be linear.

Is there clever trick I can use to incorporate this non-linearity? Otherwise, does anyone have any suggestions of other models can solve this problem?

Thanks very much in advance.