Loss robustness via Fisher-weighted squared-error loss function

Udi E. Makov

doi:10.1016/0167-6687(94)00022-7

Loss robustness via Fisher-weighted squared-error loss function

Udi E. Makov

Department of Statistics

Research output: Contribution to journal › Article › peer-review

Abstract

This paper discusses measures of loss robustness which could facilitate the specification of a loss function for estimating an unknown risk parameter. In particular risk robustness and posterior loss robustness are defined and it is shown that for the gamma distribution the Fisher-weighted squared-error loss function is robust in both senses.

Original language	English
Pages (from-to)	1-6
Number of pages	6
Journal	Insurance: Mathematics and Economics
Volume	16
Issue number	1
DOIs	https://doi.org/10.1016/0167-6687(94)00022-7
State	Published - Apr 1995

Keywords

Fisher-weighted squared-error loss function
Loss robustness
Risk robustness

ASJC Scopus subject areas

Statistics and Probability
Economics and Econometrics
Statistics, Probability and Uncertainty

Access to Document

10.1016/0167-6687(94)00022-7

Cite this

@article{5a85da556b9e456d97fea9e0bc21495d,

title = "Loss robustness via Fisher-weighted squared-error loss function",

abstract = "This paper discusses measures of loss robustness which could facilitate the specification of a loss function for estimating an unknown risk parameter. In particular risk robustness and posterior loss robustness are defined and it is shown that for the gamma distribution the Fisher-weighted squared-error loss function is robust in both senses.",

keywords = "Fisher-weighted squared-error loss function, Loss robustness, Risk robustness",

author = "Makov, \{Udi E.\}",

year = "1995",

month = apr,

doi = "10.1016/0167-6687(94)00022-7",

language = "English",

volume = "16",

pages = "1--6",

journal = "Insurance: Mathematics and Economics",

issn = "0167-6687",

publisher = "Elsevier",

number = "1",

}

TY - JOUR

T1 - Loss robustness via Fisher-weighted squared-error loss function

AU - Makov, Udi E.

PY - 1995/4

Y1 - 1995/4

N2 - This paper discusses measures of loss robustness which could facilitate the specification of a loss function for estimating an unknown risk parameter. In particular risk robustness and posterior loss robustness are defined and it is shown that for the gamma distribution the Fisher-weighted squared-error loss function is robust in both senses.

AB - This paper discusses measures of loss robustness which could facilitate the specification of a loss function for estimating an unknown risk parameter. In particular risk robustness and posterior loss robustness are defined and it is shown that for the gamma distribution the Fisher-weighted squared-error loss function is robust in both senses.

KW - Fisher-weighted squared-error loss function

KW - Loss robustness

KW - Risk robustness

UR - https://www.scopus.com/pages/publications/0348050222

U2 - 10.1016/0167-6687(94)00022-7

DO - 10.1016/0167-6687(94)00022-7

M3 - Article

AN - SCOPUS:0348050222

SN - 0167-6687

VL - 16

SP - 1

EP - 6

JO - Insurance: Mathematics and Economics

JF - Insurance: Mathematics and Economics

IS - 1

ER -

Loss robustness via Fisher-weighted squared-error loss function

Abstract

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this