User`s guide

Creating Model Structures at the Command Line
For linear models, you can use a shortcut to specify the second-level
Algorithm properties, such as Advanced. With this syntax, you can reference
the structure elds by name without specifying the structure to which these
elds belong.
However, wh en estimating nonline ar black-box models, you must set the
specic elds of the
Advanced Algorithm structure and the nonlinearity
estimators before estimation. For example, suppose you w ant to set the value
of the
wavenet object property Optio ns, which is a structure. The following
commands set the
Options values before estimation and include the modied
wavenet object in the estimator:
% Define wavenet object with defaul properti es
W = wavenet;
% Specify variable to represent Options field
O = W.Options;
% Modify values of specific Options fields
O.MaxLevels = 5 ;
O.DilationStep = 2;
% Estimate model using new Options settings
M = nlarx(data,[2 2 1],wavenet('options',O))
where O specie s the values of the Options structure elds and M is the
estimated model. For more information about these and other comm ands,
see the corresponding reference page.
V iewing Model Properties and Estimated Parameters
To view all the properties and values of any model object, use the get
command. For example, type the following at the prompt to load sample data,
compute a n ARX m odel, and list the model properties:
load iddata8
m_arx=arx(z8,[4 3 2 3 0 0 0]);
get(m_arx)
To acces s a specic property, use dot notatio n. For ex ample, to view the
A matrix containing the estimated parameters in the previous m odel, type
the following command:
m_arx.a
2-17