A unified approach to Cramér-rao inequalities

Research output: Contribution to journalArticle

Abstract

A unified approach is presented for establishing a broad class of Cramér-Rao inequalities for the location parameter, including, as special cases, the original inequality of Cramér and Rao, as well as an L p version recently established by the authors. The new approach allows for generalized moments and Fisher information measures to be defined by convex functions that are not necessarily homogeneous. In particular, it is shown that associated with any log-concave random variable whose density satisfies certain boundary conditions is a Cramér-Rao inequality for which the given log-concave random variable is the extremal. Applications to specific instances are also provided.

Original languageEnglish (US)
Article number6655985
Pages (from-to)643-650
Number of pages8
JournalIEEE Transactions on Information Theory
Volume60
Issue number1
DOIs
StatePublished - Jan 2014

Fingerprint

Random variables
Boundary conditions

Keywords

  • Cramér-Rao inequality
  • entropy
  • Fisher information
  • information measure
  • moment
  • Rényi entropy
  • Shannon entropy

ASJC Scopus subject areas

  • Information Systems
  • Computer Science Applications
  • Library and Information Sciences

Cite this

A unified approach to Cramér-rao inequalities. / Cianchi, Andrea; Lutwak, Erwin; Yang, Deane; Zhang, Gaoyong.

In: IEEE Transactions on Information Theory, Vol. 60, No. 1, 6655985, 01.2014, p. 643-650.

Research output: Contribution to journalArticle

@article{f9dfb57c5edb4ef38ee61a453bbd0c3c,
title = "A unified approach to Cram{\'e}r-rao inequalities",
abstract = "A unified approach is presented for establishing a broad class of Cram{\'e}r-Rao inequalities for the location parameter, including, as special cases, the original inequality of Cram{\'e}r and Rao, as well as an L p version recently established by the authors. The new approach allows for generalized moments and Fisher information measures to be defined by convex functions that are not necessarily homogeneous. In particular, it is shown that associated with any log-concave random variable whose density satisfies certain boundary conditions is a Cram{\'e}r-Rao inequality for which the given log-concave random variable is the extremal. Applications to specific instances are also provided.",
keywords = "Cram{\'e}r-Rao inequality, entropy, Fisher information, information measure, moment, R{\'e}nyi entropy, Shannon entropy",
author = "Andrea Cianchi and Erwin Lutwak and Deane Yang and Gaoyong Zhang",
year = "2014",
month = "1",
doi = "10.1109/TIT.2013.2284498",
language = "English (US)",
volume = "60",
pages = "643--650",
journal = "IEEE Transactions on Information Theory",
issn = "0018-9448",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "1",

}

TY - JOUR

T1 - A unified approach to Cramér-rao inequalities

AU - Cianchi, Andrea

AU - Lutwak, Erwin

AU - Yang, Deane

AU - Zhang, Gaoyong

PY - 2014/1

Y1 - 2014/1

N2 - A unified approach is presented for establishing a broad class of Cramér-Rao inequalities for the location parameter, including, as special cases, the original inequality of Cramér and Rao, as well as an L p version recently established by the authors. The new approach allows for generalized moments and Fisher information measures to be defined by convex functions that are not necessarily homogeneous. In particular, it is shown that associated with any log-concave random variable whose density satisfies certain boundary conditions is a Cramér-Rao inequality for which the given log-concave random variable is the extremal. Applications to specific instances are also provided.

AB - A unified approach is presented for establishing a broad class of Cramér-Rao inequalities for the location parameter, including, as special cases, the original inequality of Cramér and Rao, as well as an L p version recently established by the authors. The new approach allows for generalized moments and Fisher information measures to be defined by convex functions that are not necessarily homogeneous. In particular, it is shown that associated with any log-concave random variable whose density satisfies certain boundary conditions is a Cramér-Rao inequality for which the given log-concave random variable is the extremal. Applications to specific instances are also provided.

KW - Cramér-Rao inequality

KW - entropy

KW - Fisher information

KW - information measure

KW - moment

KW - Rényi entropy

KW - Shannon entropy

UR - http://www.scopus.com/inward/record.url?scp=84891538018&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84891538018&partnerID=8YFLogxK

U2 - 10.1109/TIT.2013.2284498

DO - 10.1109/TIT.2013.2284498

M3 - Article

VL - 60

SP - 643

EP - 650

JO - IEEE Transactions on Information Theory

JF - IEEE Transactions on Information Theory

SN - 0018-9448

IS - 1

M1 - 6655985

ER -