It is demonstrated that implicit constraints of the form G( theta )=0 can be incorporated into the Cramer-Rao lower bound. Constraints on the estimator restrict the local movement of the estimator theta (X) under statistical fluctuation in the observation vector X. A modified Cramer-Rao bound can be obtained by incorporating these restrictions into the formulation of the unconstrained bound. Conversely, when the parameter is constrained, the observation vector X is only allowed to vary according to the probability distribution F/sub theta /, where theta is confirmed to the constraint set. The Fisher information matrix for the case of a constrained parameter can be written as a projection of the unconstrained Fisher matrix onto a subspace defined by the constraint. Conditions under which an estimator achieves the lower bound for constrained estimation are derived, and an example of an estimator that achieves the bound for the linear Gaussian problem is presented.<<ETX>>
[1]
Michael I. Miller,et al.
The Use of Sieves to Stabilize Images Produced with the EM Algorithm for Emission Tomography
,
1985,
IEEE Transactions on Nuclear Science.
[2]
R. Inkol,et al.
The use of linear constraints to reduce the variance of time of arrival difference estimates for sou
,
1983
.
[3]
K. Vastola,et al.
Robust Wiener-Kolmogorov theory
,
1984,
IEEE Trans. Inf. Theory.
[4]
William L. Root.
Ill-posedness and precision in object-field reconstruction problems
,
1987
.
[5]
James R. Fienup,et al.
Reconstruction And Synthesis Applications Of An Iterative Algorithm
,
1984,
Other Conferences.
[6]
C. C. Wackerman,et al.
Phase-retrieval error: a lower bound
,
1987
.