Home > Research > Publications & Outputs > Bayesian signal estimation
View graph of relations

Bayesian signal estimation

Research output: Contribution to Journal/MagazineJournal articlepeer-review

<mark>Journal publication date</mark>1996
<mark>Journal</mark>Statistics and Decisions
Number of pages19
Pages (from-to)275-293
Publication StatusPublished
<mark>Original language</mark>English


The problem of Bayesian estimation of a signal contaminated by white noise is
investigated. Restricting the unknown signal to a compact subset of L2([0, 1]), the existence of a unique Bayes estimator for the squared-error loss and its robustness with respect to the prior used are established; for sufficiently diffuse priors, the Bayes estimator is shown to be uniformly L1-consistent.