Complete class theorem
≈ 2 min read
Names in other languages
No names in other languages are held for this entry yet.
Article bodies are English and are not machine-translated. A name in another language is not a translation of the article.
The Complete class theorems is a class of theorems in decision theory. They establish that all admissible decision rules are equivalent to the Bayesian decision rule for some utility function and some prior distribution (or for the limit of a sequence of prior distributions). Thus, for every decision rule, either the rule may be reformulated as a Bayesian procedure (or a limit of a sequence of such), or there is a rule that is sometimes better and never worse. For example, Ferguson [section 2.10] gives a theorem establishing that if the sample space is closed and the parameter space is finite then the class of Bayes rules is complete.
The Complete class theorems is a class of theorems in decision theory. They establish that all admissible decision rules are equivalent to the Bayesian decision rule for some utility function and some prior distribution (or for the limit of a sequence of prior distributions). Thus, for every decision rule, either the rule may be reformulated as a Bayesian procedure (or a limit of a sequence of such), or there is a rule that is sometimes better and never worse. For example, Ferguson [section 2.10] gives a theorem establishing that if the sample space is closed and the parameter space is finite then the class of Bayes rules is complete.
References
Text derived from https://en.wikipedia.org/w/index.php?oldid=1344098416 under CC BY-SA 4.0; modifications have been made.