Some classes of global Cramér-Rao bounds (Q1101155)

Cramér-Rao type bounds for the estimation error of a parameter in a Bayesian set-up introduced by \textit{H. L. Van Trees} [Detection, estimation and modulation theory, I. (1968; Zbl 0202.180)] proved useful in various stochastic communication and control problems. The present paper addresses basically two issues. The first deals with a comparison of the tightness of several different versions of the mentioned bound in the multivariate case. The second introduces several useful generalizations of the original version of the bound.