The Identification of Errors-in-variables Models with Dynayics Xichael Green Lyd Brain

5!Y ) if oXy > o The paper considers the task of identifying a xx Oxy causal, linear, dynamic, multivariable system excited by stationary, zero-mean noise of unknown spectrum, and [k, %Y ] if oxy < 0 given measurements of the system inputs and outputs O X X contaminated by independent, additive noise also of unknown soectra. Although the solution is in general 0 if oxv = 0 . not unique, finite-dimensional parameterizatians of the solution set are given, even though the various spectra For the dynamic case, let YY may not be rational.