Title :
Relative sufficiency
Author :
Popoli, Robert F. ; Mendel, Jerry M.
Author_Institution :
Dept. of Electr. Eng.-Syst., Univ. of Southern California, Los Angeles, CA, USA
fDate :
5/1/1993 12:00:00 AM
Abstract :
By the classical definition of a sufficient statistic, either a statistic is or is not sufficient. A measure called relative sufficiency, by which the degree of sufficiency can be defined for the problem of random parameter estimation is presented. It is shown that relative sufficiency is equivalent to the Kullback-Leibler information measure. Its calculation and interpretation are illustrated for the estimation of a scalar random variable
Keywords :
parameter estimation; random functions; Kullback-Leibler information measure; random parameter estimation; relative sufficiency; scalar random variable; Approximation methods; Automatic control; Control systems; Frequency response; Parameter estimation; Polynomials; Random variables; Statistics; System identification; Transfer functions;
Journal_Title :
Automatic Control, IEEE Transactions on
