System Identification Toolbox    

Complex-Valued Data

Some applications of system identification work with complex-valued data, and thus create complex-valued models. Most of the routines in the System Identification Toolbox support complex data and models. This is true for the estimation routines ar, armax, arx, bj, covf, ivar, iv4, oe, pem, spa, and n4sid. The transformation routines, like freqresp, zpkdata, etc., also work for complex-valued models, but no pole-zero confidence regions are given. Note also that the parameter variance-covariance information then refers to the complex valued parameters, so no separate information about the accuracy of the real and imaginary parts will be given. Some display functions like compare and plot do not work for the complex case. Use sim and plot real and imaginary parts separately.


  Enumeration of Estimated Parameters Strange Results