(...)
> But we have missing observations... How can we handle this?
I have no idea how this could work, in a time-series model with
lags. That's why I went for the combined version.
Dear Allin, I made a deeper analysis in the RATS operationalization and I discovered that what it does is equivalent to put zeros at the "NA" observations:
<script>
open australia.gdt
list Y = PAU IAU E
series z = normal()
scalar tau = 1.5
series r1 = z(-1) >= tau
series r2 = 1-r1
loop foreach i Y
series $i_r1 = r1 * $i
series $i_r2 = r2 * $i
endloop
list regime1 = *_r1
list regime2 = *_r2
</script>