User`s guide

Estimating AR and A RMA Models
Estimating AR and ARMA Models
In this section...
“Definition of AR and ARMA Models” on page 6-7
“Estimating Polynomial Time-Series M odels in the GUI” on page 6-7
“Estimating AR and ARMA Models at the Command Line” on page 6-10
Definition of AR and ARM A Models
For a single-output signal y(t), the AR model is given by the following equation:
Aqyt et( ) () ()=
The AR model is a special case of the A RX model w ith no input.
The ARMA model for a single-output time-series is given by the following
equation:
Aqyt Cqet()() ()()=
The ARMA struc
ture reduces to the AR structure for C(q)=1. The ARMA
model is a spe
cial case of the ARMA X model with no input.
For more info
rmation about polynomial models, see “What Are Black-Box
Polynomial M
odels?” on page 3-41.
Estimating P
olynomial Time-Series Models in the GUI
Before you be
gin, you must have accomplished the following:
• Prepared the
data, a s d escribe d in “Preparing T ime-Series Data” on page
6-3
• Estimated mo
del order, as described in “Preliminary Step – E stimating
Model Order
s and Input Delays” on page 3-49
6-7