User`s guide

3 Linear Model Identification

Similarly, to view the properties and values of the EstimationInfo

structure, type the following command:

m_armax.EstimationInfo

This action displays the complete list of read-only Estimation Info

properties and values that describe the estimation data set, quantitative

measures of model quality (loss function and FPE), the number of iterations

actually used, and the behavior of the iterative model estimation.

ans =

Status: 'Estima ted model (PEM)'

Method: 'ARMAX'

LossFcn: 0.9602

FPE: 1.0263

DataName: 'z8 '

DataLength: 500

DataTs: 1

DataDomain: 'Ti me'

DataInterSample: {3x1 cell}

WhyStop: 'Near (local) minimum, (norm(g)<tol).'

UpdateNorm: 8.0 572e -006

LastImprovement: '7.4611e-006%'

Iterations: 4

InitialState: 'Zero'

Warning: 'None'

6 If you want to repeat the model estimation using differen t mo del orders,

but keep the algorithm propertie s the same, you can store the model

properties used for

m_armax in a variable, as follows:

myAlg=m_armax.Algorithm

This action stores the speciﬁed focus, tolerance,andmaxiter,andthe

default algorithm .

7 To reuse the algorithm properties in estimating the ARMAX model with

different orders, use the following co mmand:

m_armax2=armax(z8,[4 3 2 3 3 1 1 1],...

'algorithm',myAlg);

3-72