On estimating the information fraction being induced by a finite sequence of moments

被引：0

作者：

Zang, Yishan ^{[1
]}

Provost, Serge B. ^{[1
]}

Ades, Michel ^{[2
]}

机构：

[1] Univ Western Ontario, Dept Stat & Actuarial Sci, London, ON N6A 5B7, Canada

[2] Univ Quebec Montreal, Dept Math, Montreal, PQ, Canada

来源：

COMMUNICATIONS IN STATISTICS-THEORY AND METHODS | 2025年

基金：

加拿大自然科学与工程研究理事会;

关键词：

Information; moments; entropy; Kullback-Leibler divergence; Fritsch-Carlson monotonic interpolation;

D O I：

10.1080/03610926.2025.2461605

中图分类号：

O21 [概率论与数理统计]; C8 [统计学];

学科分类号：

020208 ; 070103 ; 0714 ;

摘要：

This article introduces a methodology for quantifying the proportion of information that sets of consecutive moments contain. The proposed approach relates a sequence of moments, up to a given order, to certain points that are deemed representative of the target distribution. It involves the use of Fritsch-Carlson monotonic interpolants in conjunction with the Kullback-Leibler measure of divergence. Four illustrative examples are presented.

引用

页数：21