User`s guide

Overview of Model Validation and Plots
• Analyzing model response. For more information, see the following:
- “Using Impulse- and Step-Response Plots to Validate Models” on page
8-24
- “Using Frequency-R esponse Plots to Validate Models” on page 8-32
For information about the response of the noise model, see “Creating
Noise-Spectrum Plots” on page 8-40.
• Plotting the poles and zeros of the linear parametric model.
For more informatio n, see “Using Pole-Zero Plots to V alidate M odels” on
page 8-47.
• Comparing the response of nonparametric models, such as impulse-, step-,
and frequency-response models, to parametric models, s uch as linear
polynomial models, state-space model, and nonlinear parametric models.
Note Do not u se this comparison when feedback is present in the sy stem
because feedback makes nonparametric models unreliable. To test if
feedbackispresentinthesystem,usethe
advice command on the data.
• Compare models using Akaike Information Criterion or Akaike Final
Prediction Error.
For more information, se e the
aic and fpe reference page.
• Plotting linear and nonlinear blocks of Hammerstein-Wiener and nonlinear
ARX models.
For more informa ti on, see “Usi ng Hamm erstein-Wiener Plots to Validate
Models” on page 8-56 and “Using Nonlinear ARX Plots to Validate Models”
on page 8-52.
Displaying confidence intervals on supported plots helps you assess the
uncertainty of model parameters. Fo r more information, see “Computing
Model U ncertainty” on page 8-64.
8-3