Forcast function for ARMA models

2 views (last 30 days)
Patricia Alejandra Palacios Romero
Commented: Aman on 1 Oct 2024
I'm trying to use the built-in function forecast. But when I apply it I'm just getting a constant value. Is there any reason for that? or am I just using it wrong? Here is more or less the code:
toEstMdl = arima(2,0,0);
EstMdl = estimate(toEstMdl,Residuals);
estValues = forecast(EstMdl,k);
  1 Comment
Aman
Aman on 1 Oct 2024
As per my understanding below could be the possible reasons why you are getting constant value as the output of the "forecast" function:
  • The (2,0,0) model implies an AR(2) model with no differencing and no MA terms. Ensure this is the correct specification for your data.
  • 'k' should be a positive integer indicating how many steps ahead you want to forecast.
  • If the model includes a constant term and the data is mean-reverting around a constant level, forecasts can appear constant, especially if no trend or seasonal components are present.
Please try to analyse your code as per the above. Hope it helps!

Sign in to comment.

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!