User`s guide

8 Model Analysis
Because of the definition of Best Fit, it is possible for this value to b e negative.
A negative best fit is worse than 0% and can occur for the following reasons:
• The estima t ion alg ori th m fai led to converg e.
• The m odel was not estimated by minimizing
yy−
ˆ
. Best Fit can
be negative wh en you minimized 1-step-ahead prediction during the
estimation, but validate using the simulated output
ˆ
y
.
• The v alidation d ata set was not preprocess ed in the same way as the
estimation data set.
Thefollowingtablesummarizesthe Model Output plot settings.
ModelOutputPlotSettings
Action
Command
Display con fidence intervals.
Note Confidence intervals are o nly
available for s imulated model output
of linear models. Con fidence internal
are not available for nonlinear ARX
and Hammerstein-Wiener models.
• To displa y the dashed lines on
either side of the nom inal model
curve, select Options > Show
confiden ce intervals. Select
this option again to hide the
confidence intervals.
• To change the confidence
value, select Options > Set %
confidence level, and choose a
value from the list.
• To enter your own confidence
level, select Options > Set
confidence level > Other.
Enter the value as a probability
(between 0 and 1) or as the
number of standard deviations of
a Gaussian distribution.
8-12