A representation theorem and applications to measure selection and 
noninformative priors

Jaeger, Manfred

アイテム詳細

登録内容を編集ファイル形式で保存

一時保存へ追加

タグ情報を表示リリース履歴を表示詳細要約

公開

報告書

A representation theorem and applications to measure selection and noninformative priors

MPS-Authors

/persons/resource/persons44689

Jaeger, Manfred
Programming Logics, MPI for Informatics, Max Planck Society;

External Resource

There are no locators available

Fulltext (restricted access)

There are currently no full texts shared for your IP range.

フルテキスト (公開)

2003-2-002
(全文テキスト（全般）), 10KB

付随資料 (公開)

There is no public supplementary material available

引用

Jaeger, M.(2003). A representation theorem and applications to measure selection and noninformative priors (MPI-I-2003-2-002). Saarbrücken: Max-Planck-Institut für Informatik.

引用: https://hdl.handle.net/11858/00-001M-0000-0014-6AFE-E

要旨

We introduce a set of transformations on the set of all probability distributions over a finite state space, and show that these transformations are the only ones that preserve certain elementary probabilistic relationships. This result provides a new perspective on a variety of probabilistic inference problems in which invariance considerations play a role. Two particular applications we consider in this paper are the development of an equivariance-based approach to the problem of measure selection, and a new justification for Haldane's prior as the distribution that encodes prior ignorance about the parameter of a multinomial distribution.