DocumentCode :
850623
Title :
Sufficient sequences and state-space models for random processes
Author :
Dickinson, Bradley W.
Author_Institution :
Princeton University, Princeton, NJ, USA
Volume :
31
Issue :
1
fYear :
1986
fDate :
1/1/1986 12:00:00 AM
Firstpage :
89
Lastpage :
91
Abstract :
Let ( 
, ...) be a sequence of observed random variables whose probability distributions are described by a parameterized family of density functions 
. If there exists a sequence of sufficient statistics for 
, 
, ...), and if a realizability assumption holds, then there is a finite-dimensional state-space model whose output process agrees with ( , ...) in distribution.
, ...) be a sequence of observed random variables whose probability distributions are described by a parameterized family of density functions . If there exists a sequence of sufficient statistics for , , ...), and if a realizability assumption holds, then there is a finite-dimensional state-space model whose output process agrees with ( , ...) in distribution.Keywords :
Parameter estimation; Stochastic systems; Adaptive control; Adaptive filters; Adaptive systems; Density functional theory; Helium; Production; Random processes; Silicon compounds; Stability analysis; Statistical distributions;
fLanguage :
English
Journal_Title :
Automatic Control, IEEE Transactions on
Publisher :
ieee
ISSN :
0018-9286
Type :
jour
DOI :
10.1109/TAC.1986.1104103
Filename :
1104103
Link To Document :
