Specifying Initial States for Iterative Estimation Algorithms

When you use the pem or polyest functions to estimate ARMAX, Box-Jenkins (BJ), Output-Error (OE), you must specify how the algorithm treats initial conditions.

This information supports the estimation procedures Estimate Polynomial Models in the App and Using polyest to Estimate Polynomial Models.

In the System Identification app, for ARMAX, OE, and BJ models, set Initial state to one of the following options:

• Auto — Automatically chooses Zero, Estimate, or Backcast based on the estimation data. If initial states have negligible effect on the prediction errors, the initial states are set to zero to optimize algorithm performance.

• Zero — Sets all initial states to zero.

• Estimate — Treats the initial states as an unknown vector of parameters and estimates these states from the data.

• Backcast — Estimates initial states using a smoothing filter.

At the command line, specify the initial conditions as an estimation option. Use polyestOptions to configure options for the polyest command, armaxOptions for the armax command etc. Set the InitialCondition option to the desired value in the option set. For example, use this command to estimate an ARMAX model and set the initial states to zero:

opt = armaxOptions('InitialCondition','zero');
m = armax(data,[2 2 2 3],opt);

For a complete list of values for the InitialCondition estimation option, see the armaxOptions reference page.