Dynamic realizations of sufficient sequences

Let (U_{1},U_{2}, \cdots) be a sequence of observed random variables and (T_{1}(U_{1}),T_{2}(U_{1}, U_{2}), \cdots) be a corresponding sequence of sufficient statistics (a sufficient sequence). Under certain regularity conditions, the sufficient sequence defines the input/output map of a time-varying, discrete-time nonlinear system. This system provides a recursive way of updating the sufficient statistic as new observations are made. Conditions are provided assuring that such a system evolves in a state space of minimal dimension. Several examples are provided to illustrate how this notion of dimensional minimality is related to other properties of sufficient sequences. The results can be used to verify the form of the minimum dimension (discrete-time) nonlinear filter associated with the autoregressive parameter estimation problem.

[1]  Carla A. Schwartzt,et al.  Characterizing innovations realizations for random processes , 1984 .

[2]  J. L. Denny Note on a Theorem of Dynkin on the Dimension of Sufficient Statistics , 1969 .

[3]  Mátyás Arató,et al.  On the Sufficient Statistics for Stationary Gaussian Random Processes , 1961 .

[4]  Eduardo D. Sontag,et al.  Realization Theory of Discrete-Time Nonlinear Systems: Part I - The Bounded Case , 1979 .

[5]  Bradley W. Dickinson,et al.  Properties and applications of Gaussian autoregressive processes in detection theory , 1981, IEEE Trans. Inf. Theory.

[6]  Jürgen O. Gobien,et al.  Sufficient statistics and reproducing densities in simultaneous sequential detection and estimation , 1973, IEEE Trans. Inf. Theory.

[7]  Thomas Kailath,et al.  A view of three decades of linear filtering theory , 1974, IEEE Trans. Inf. Theory.

[8]  R. R. Bahadur Sufficiency and Statistical Decision Functions , 1954 .

[9]  L. Brown Sufficiency Statistics in the Case of Independent Random Variables , 1964 .

[10]  Günther Sawitzki,et al.  Exact filtering in exponential families: Discrete time , 1981 .

[11]  Sawitzki GÜnther,et al.  Finite dimensional filter systems in discrete time , 1981 .

[12]  Ryoichi Shimizu,et al.  Remarks on sufficient statistics , 1966 .

[13]  T. Kailath,et al.  An innovations approach to least-squares estimation--Part VI: Discrete-time innovations representations and recursive estimation , 1973 .

[14]  T. W. Anderson DETERMINATION OF THE ORDER OF DEPENDENCE IN NORMALLY DISTRIBUTED TIME SERIES , 1962 .

[15]  J L Denny,et al.  Sufficient conditions for a family of probabilities to be exponential. , 1967, Proceedings of the National Academy of Sciences of the United States of America.

[16]  Salvatore Monaco,et al.  On the realization of nonlinear discrete-time systems , 1984 .

[17]  J. A. Bather,et al.  Invariant Conditional Distributions , 1965 .