The Model output window is opened by checking the corresponding check box in the ident window.
The plots show the simulated (predicted) outputs of selected models. The models are fed with inputs from the Validation Data set, which is plotted in white.
The mean square fit between the measured output and the simulated/predicted output is displayed at the side of the plot.
There are submenus under the Options menu, which allow you to choose between simulated and predicted model output. There are also options to show measured and model outputs together or to show the difference between them.
An intuitive interpretation of a K-step ahead predicted output is to see it as a result of a simulation, using the actual input, that was started at the correct (measured) output level K samples earlier. K is called the prediction horizon. It can be changed under the Options submenu Set prediction horizon.
The mean square fit is defined as sqrt(sum((y(t)-ys(t)).^2)/N), where N is the number of data points. The span over which the fit is measured can be changed under the Options submenu Customized time span for fit.
(file compare.htm)