Answers are grounded in this paper and cite their sources.
Summary It is shown that a linear ordering of the parameter space is a useful generalization of classical estimates, and that for a certain class of loss functions, Bayes decision procedures lead to very simple linear orderings.
No takes yet. Share an insight, caveat, or question.
J. A. Hartigan (1966) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: