Sufficiency in bayesian models
Volume 25 / 1998
Applicationes Mathematicae 25 (1998), 113-120
DOI: 10.4064/am-25-1-113-120
Abstract
We consider some fundamental concepts of mathematical statistics in the Bayesian setting. Sufficiency, prediction sufficiency and freedom can be treated as special cases of conditional independence. We give purely probabilistic proofs of the Basu theorem and related facts.