Finite record effects of the Errors-In-Variables estimator for linear dynamic systems

摘要

The frequency domain errors-in-variables (EIV) estimator for linear dynamic systems is generally formulated as a weighted least square estimator, where the weights used are the estimated noise (co)variances. In this paper, we study the finite record influences on the uncertainty of the EIV estimator for using the estimated weights. Furthermore, we discuss when a significant influence can occur and derive a practical method to circumvent this problem without the need of introducing a parametric noise model.