Kalman Filter with Panel Data

[abentley]

Is it true that the state space objects cannot handle vectors of time series data? If so does anybody have any suggestions as to how one could apply a k-filter to a panel data set...
I am new to e-views so I could be confused, but this seems to be a fairly considerable constraint to place on state space objects...any advice or guidance would be appreciated. Thanks.

[EViews Glenn]

There is no support in panel workfiles. You could do the estimation in unstacked panel form.

To be honest, we haven't had a lot of requests for this, but I'll put it on the list of things to look into. The real issue is what exactly people want to do with the panel structure (i.e., how does the cross-section heterogeneity affect the specification). For small numbers of cross-sections, I'd be inclined to simply estimate in unstacked form.