Asymptotic normality of prediction error estimators for approximate system models

A general class of parameter estimation methods for stochastic dynamical systems is studied. The class contains the least squares method, output-error methods, the maximum likelihood method and several other techniques. It is shown that the class of estimates so obtained are asymptotically normal and expressions for the resulting asymptotic covariance matrices are given. The regularity conditions that are imposed to obtain these results, are fairly weak. It is, for example, not assumed that the true system can be described within the chosen model set, and, as a consequence, the results in this paper form a part of the so-called approximate modeling approach to system identification. It is also noteworthy that arbitrary feedback from observed system outputs to observed system inputs is allowed and stationarity is not required

[1]  M. S. Bartlett,et al.  Some probability limit theorems with statistical applications , 1953, Mathematical Proceedings of the Cambridge Philosophical Society.

[2]  Steven Orey,et al.  A central limit theorem for $m$-dependent random variables , 1958 .

[3]  T. W. Anderson.  On Asymptotic Distributions of Estimates of Parameters of Stochastic Difference Equations , 1959 .

[4]  K. Åström,et al.  Numerical Identification of Linear Dynamic Systems from Normal Operating Records , 1966 .

[5]  B. Rosén,et al.  On the central limit theorem for sums of dependent random variables , 1967 .

[6]  H. Akaike.  Maximum likelihood identification of Gaussian autoregressive moving average models , 1973 .

[7]  P. Caines.  Prediction error identification methods for stationary stochastic processes , 1976 .

[8]  L. Ljung.  On Consistency and Identifiability , 1976 .

[9]  E. J. Hannan,et al.  Vector linear time series models , 1976, Advances in Applied Probability.

[10]  Lennart Ljung,et al.  On The Consistency of Prediction Error Identification Methods , 1976 .

[11]  P. Caines.  Stationary linear and non-linear system identification and predictor set completeness , 1977 .

[12]  Lennart Ljung,et al.  Prediction Error Identification Methods , 1978 .

[13]  L. Ljung.  Convergence analysis of parametric identification methods , 1978 .

[14]  Lennart Ljung,et al.  Validation of Approximate Models Obtained from Prediction Error Identification , 1978 .

[15]  John B. Moore,et al.  Model approximations via prediction error identification , 1978, Autom..