[Date Prev][Date Next][Thread Prev][Thread Next][Date index][Thread index]
st: Confidence intervals in time series
I'm working in Stata9 SE for Windows with the following time series
model: arima x, arima(p,d,q) sarima(P,D,Q,S) noconstant. I already
have forecasted values and now I'm interested in finding the
confidence intervals for those values.
I've tried finding the standar errors of the prediction with "predict
x_error, stdp" but Stata gives me the following error "variable ma not
found". I know I'm getting this error because the lack of a constant
term, but when I have it "x_error " contains in every observation the
standar error of the constant.
I've also tried with predictnl but somehow I can't figure out the rigth syntax.
Can anybody help me with this?
Thank you very much
* For searches and help try: