In Chapter 7 we described a number of different methods to determine models from data. To use these methods in practice, we need insight into their properties: How well will the identified model describe the actual system? Are some identification methods better than others? How should the design variables associated with a certain method be chosen?
Such questions relate, from a formal point of view, to the mapping (7.7) from the data set ZN to the parameter estimate :
Questions about properties ...