Error With Forecasting ARIMAX Model

26 views (last 30 days)
J.C.
J.C. on 27 Mar 2014
Commented: Redho redho on 22 Dec 2020
I'm trying to specify an ARIMAX model and then use it to forecast an hourly time series. When I use forecast, however, I get the error: "Error using arima/forecast (line 274) Additive constant must be specified." I'm sure I missing something simple, but I can't figure out what it is and searching the web hasn't turned up anything. The relevent code is below. Any help would be appreciated.
model = arima('AR', arLagV, 'D', 0, 'SAR', 0);
[estModel, estParmCov, logL, info] = estimate(model, Y(100:length(Y)),...
'X', X, 'Display', 'params');
[Y,YMSE,V] = forecast(model, 48, 'X0', X, 'Y0', Y(100:length(Y)), 'XF', XF);
  1 Comment
Redho  redho
Redho redho on 22 Dec 2020
excuse me, could you help me sir with give me this codes because i need to toward a bachelor degree
thanks before sir

Sign in to comment.

Accepted Answer

Hang Qian
Hang Qian on 30 Mar 2014
To forecast the ARIMA model, we want a model with all coefficients being known. After parameter estimation, the fitted model is reported as estModel. So the program will work if you replace "model" by "estModel":
[Y,YMSE,V] = forecast(estModel, 48, 'X0', X, 'Y0', Y(100:length(Y)), 'XF', XF);

More Answers (0)

Categories

Find more on Conditional Mean Models in Help Center and File Exchange

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!