A characterization of probability densities with expected log likelihood

Ryuei Nishii

doi:10.1080/03610928908830056

A characterization of probability densities with expected log likelihood

Ryuei Nishii

研究成果: ジャーナルへの寄稿 › 学術誌 › 査読

抄録

In the class of all densities with constraints E b_i(X) = Cj, (i = 1, q), it is we I 1 known that the entropy is maximized by the density belonging to the exponential family specified by b.(x). i = 1.q. Our aim in this note is to generalize the result by using expected log likelihood.

本文言語	英語
ページ（範囲）	2657-2662
ページ数	6
ジャーナル	Communications in Statistics - Theory and Methods
巻	18
号	7
DOI	https://doi.org/10.1080/03610928908830056
出版ステータス	出版済み - 1月 1 1989
外部発表	はい

!!!All Science Journal Classification (ASJC) codes

統計学および確率

文献へのアクセス

10.1080/03610928908830056

他のファイルとリンク

引用スタイル

@article{8bf2e928ef434c59b004d528625340ee,

title = "A characterization of probability densities with expected log likelihood",

abstract = "In the class of all densities with constraints E bi(X) = Cj, (i = 1, q), it is we I 1 known that the entropy is maximized by the density belonging to the exponential family specified by b.(x). i = 1.q. Our aim in this note is to generalize the result by using expected log likelihood.",

author = "Ryuei Nishii",

year = "1989",

month = jan,

day = "1",

doi = "10.1080/03610928908830056",

language = "English",

volume = "18",

pages = "2657--2662",

journal = "Communications in Statistics - Theory and Methods",

issn = "0361-0926",

publisher = "Taylor and Francis Ltd.",

number = "7",

}

TY - JOUR

T1 - A characterization of probability densities with expected log likelihood

AU - Nishii, Ryuei

PY - 1989/1/1

Y1 - 1989/1/1

N2 - In the class of all densities with constraints E bi(X) = Cj, (i = 1, q), it is we I 1 known that the entropy is maximized by the density belonging to the exponential family specified by b.(x). i = 1.q. Our aim in this note is to generalize the result by using expected log likelihood.

AB - In the class of all densities with constraints E bi(X) = Cj, (i = 1, q), it is we I 1 known that the entropy is maximized by the density belonging to the exponential family specified by b.(x). i = 1.q. Our aim in this note is to generalize the result by using expected log likelihood.

UR - https://www.scopus.com/pages/publications/84973076595

UR - https://www.scopus.com/pages/publications/84973076595#tab=citedBy

U2 - 10.1080/03610928908830056

DO - 10.1080/03610928908830056

M3 - Article

AN - SCOPUS:84973076595

SN - 0361-0926

VL - 18

SP - 2657

EP - 2662

JO - Communications in Statistics - Theory and Methods

JF - Communications in Statistics - Theory and Methods

IS - 7

ER -

A characterization of probability densities with expected log likelihood

抄録

!!!All Science Journal Classification (ASJC) codes

文献へのアクセス

他のファイルとリンク

フィンガープリント

引用スタイル