SEQUENTIAL ESTIMATION FOR THE SPECTRAL DENSITY
PARAMETER OF A STATIONARY GAUSSIAN PROCESS
Abstract: In this paper we consider the problem of sequential estimation for the
stationary zero - mean Gaussian process whose spectral density is of the form
where is an unknown parameter. We find the class of Markov
stopping times determining optimal sequential estimation plans for a given function A
sequential plan is optimal if the lower bound in the information inequality is attained.
Moreover, the form of efficient sequential estimators is derived and the class of efficiently
estimable functions is investigated.
2000 AMS Mathematics Subject Classification: Primary: -; Secondary: -;
Key words and phrases: -