Page 1 of 1

State Space Covariance

Posted: Thu Sep 12, 2019 5:12 am
by ErikSpanberg
Hello!

I have a question regarding state space output.

Let's say I have a state space object "SSOBJECT". Does SSOBJECT.@Sm_statecov produce COV(state_{t|T}) or COV(state_t, state_T)?

If it's not the latter, is there any way to get COV(state_t, state_T)?

/Erik

Re: State Space Covariance

Posted: Thu Sep 12, 2019 12:23 pm
by EViews Glenn
The former.

Do you want cov(state(t|T), state(T|T))?

I haven't looked at this in a while, but off the top of my head, I can't think of an easy way to get that one from what we provide you. I'll have to take a look at the papers again.

Re: State Space Covariance

Posted: Thu Sep 12, 2019 12:45 pm
by EViews Glenn
My 2 minute look at the De Jong and Mackinnon (1988) paper suggests that if the above is indeed what you want, you can get it by saving the one-step ahead and filtered state covariances and doing a recursion. This is based on a quick look so I may be wrong, but it looks as though it's possible from the results that we offer, but unfortunately, not built-in.

The only thing that we don't have a easy way of extracting is the dated T transition matrix, but that shouldn't be too hard to obtain.

Piet De Jong and Murray J. Mackinnon
Biometrika, Vol. 75, No. 3 (Sep., 1988), pp. 601-602

Re: State Space Covariance

Posted: Tue Sep 17, 2019 2:38 am
by ErikSpanberg
Yes, that is indeed what I want. I'll look into that. Thank you

Re: State Space Covariance

Posted: Tue Sep 17, 2019 5:16 am
by ErikSpanberg
I solved it and it worked perfectly, thanks for quick response.