Any estimated model has a degree of uncertainty. This will affect the reliability of the various model properties. All the different model views (except K-step ahead prediction in the Model output View) therefore come with estimated accuracy measures.
Note that models computed by the N4SID method do not offer any uncertainty estimate.
The uncertainty region is marked by two dash-dotted lines on either side of the nominal model curve and has the same color as the curve.
The statistical interpretation is that (with the indicated probability) the true system's response will be found within the confidence region marked.
A word of caution: This interpretation assumes that the system can be described within the chosen model class. It thus assumes that the model has passed proper validation tests. The calculations are also made under the assumption that the model errors are small.
The level of confidence (or equivalently, the number of standard deviations of a Gaussian distribution) can be set arbitrarily using the Options submenu Set confidence.
Note: In the Model resids and the Transient resp (Impulse Response + Stem Plot) Views, the confidence lines are on either side of zero.
See BODE, NYQUIST, TFDATA, SSDATA and ZPKDATA in the manual for more information on uncertainty measures.
(file iduiconf.htm)