A minimally informative likelihood for decision analysis: Illustration and robustness

Ao Yuan, Bertrand S. Clarke

Research output: Contribution to journalArticle

8 Citations (Scopus)

Abstract

The authors discuss a class of likelihood functions involving weak assumptions on data generating mechanisms. These likelihoods may be appropriate when it is difficult to propose models for the data. The properties of these likelihoods are given and it is shown how they can be computed numerically by use of the Blahut-Arimoto algorithm. The authors then show how these likelihoods can give useful inferences using a data set for which no plausible physical model is apparent. The plausibility of the inferences is enhanced by the extensive robustness analysis these likelihoods permit.

Original languageEnglish (US)
Pages (from-to)649-665
Number of pages17
JournalCanadian Journal of Statistics
Volume27
Issue number3
DOIs
StatePublished - Sep 1999

Fingerprint

Decision Analysis
Likelihood
Robustness
Robustness Analysis
Likelihood Function
Physical Model
Decision analysis

Keywords

  • Blahut-Arimoto algorithm
  • Information
  • Rate distortion function
  • Robustness

ASJC Scopus subject areas

  • Statistics and Probability
  • Statistics, Probability and Uncertainty

Cite this

A minimally informative likelihood for decision analysis : Illustration and robustness. / Yuan, Ao; Clarke, Bertrand S.

In: Canadian Journal of Statistics, Vol. 27, No. 3, 09.1999, p. 649-665.

Research output: Contribution to journalArticle

@article{88137e42fdd44c2284f23cfc5509163d,
title = "A minimally informative likelihood for decision analysis: Illustration and robustness",
abstract = "The authors discuss a class of likelihood functions involving weak assumptions on data generating mechanisms. These likelihoods may be appropriate when it is difficult to propose models for the data. The properties of these likelihoods are given and it is shown how they can be computed numerically by use of the Blahut-Arimoto algorithm. The authors then show how these likelihoods can give useful inferences using a data set for which no plausible physical model is apparent. The plausibility of the inferences is enhanced by the extensive robustness analysis these likelihoods permit.",
keywords = "Blahut-Arimoto algorithm, Information, Rate distortion function, Robustness",
author = "Ao Yuan and Clarke, {Bertrand S.}",
year = "1999",
month = "9",
doi = "10.2307/3316119",
language = "English (US)",
volume = "27",
pages = "649--665",
journal = "Canadian Journal of Statistics",
issn = "0319-5724",
publisher = "Statistical Society of Canada",
number = "3",

}

TY - JOUR

T1 - A minimally informative likelihood for decision analysis

T2 - Illustration and robustness

AU - Yuan, Ao

AU - Clarke, Bertrand S.

PY - 1999/9

Y1 - 1999/9

N2 - The authors discuss a class of likelihood functions involving weak assumptions on data generating mechanisms. These likelihoods may be appropriate when it is difficult to propose models for the data. The properties of these likelihoods are given and it is shown how they can be computed numerically by use of the Blahut-Arimoto algorithm. The authors then show how these likelihoods can give useful inferences using a data set for which no plausible physical model is apparent. The plausibility of the inferences is enhanced by the extensive robustness analysis these likelihoods permit.

AB - The authors discuss a class of likelihood functions involving weak assumptions on data generating mechanisms. These likelihoods may be appropriate when it is difficult to propose models for the data. The properties of these likelihoods are given and it is shown how they can be computed numerically by use of the Blahut-Arimoto algorithm. The authors then show how these likelihoods can give useful inferences using a data set for which no plausible physical model is apparent. The plausibility of the inferences is enhanced by the extensive robustness analysis these likelihoods permit.

KW - Blahut-Arimoto algorithm

KW - Information

KW - Rate distortion function

KW - Robustness

UR - http://www.scopus.com/inward/record.url?scp=0346994181&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=0346994181&partnerID=8YFLogxK

U2 - 10.2307/3316119

DO - 10.2307/3316119

M3 - Article

AN - SCOPUS:0346994181

VL - 27

SP - 649

EP - 665

JO - Canadian Journal of Statistics

JF - Canadian Journal of Statistics

SN - 0319-5724

IS - 3

ER -