Re: [Gretl-users] Estimation of a State Space Model with Exogenous Variables in the State Transition Equation
Am 21.08.2015 um 15:52 schrieb Fernando Fernandes Neto:
Basically, in this paper, it is implemented and calibrated a State
Space
model using a Kalman Filter, where exogenous variables appear in both
Measurement Equation and State Transition Equation.
Hence, I'd like to know if it is possible to implement and calibrate
such kind of model in GRETL. If yes, how would I do that?
Hi Fernando,
after thinking only a little about it, I have two kinds of answers:
First, I am not aware that explicitly putting exogenous variables into
the state transition equation is possible in gretl. I may be wrong, however.
Secondly, my guess is that if the state transition depends on exogenous
factors, it could/should be possible to model this as a time-varying
transition matrix. Treating the transition matrix as time-varying is
possible in gretl's state-space implementation AFAIK. In this case it
would probably help to include a constant term into the state equation,
too, (which is possible in gretl now I think) in order to avoid
automatic interaction effects between the lagged state and the exogenous
terms.
In any case, Jack is the expert in this area of gretl.
HTH,
sven