# On maximum entropy priors and a most likely likelihood in auditing.

Agustín Hernández Bastida; María del C. Martel Escobar; Francisco José Vázquez Polo

Qüestiió (1998)

- Volume: 22, Issue: 2, page 231-242
- ISSN: 0210-8054

## Access Full Article

top## Abstract

top## How to cite

topHernández Bastida, Agustín, Martel Escobar, María del C., and Vázquez Polo, Francisco José. "On maximum entropy priors and a most likely likelihood in auditing.." Qüestiió 22.2 (1998): 231-242. <http://eudml.org/doc/40256>.

@article{HernándezBastida1998,

abstract = {There are two basic questions auditors and accountants must consider when developing test and estimation applications using Bayes' Theorem: What prior probability function should be used and what likelihood function should be used. In this paper we propose to use a maximum entropy prior probability function MEP with the most likely likelihood function MLL in the Quasi-Bayesian QB model introduced by McCray (1984). It is defined on an adequate parameter. Thus procedure only needs an expected value of θ0 known (in this paper the expected tainting) to obtain a MEP all an auditor or accountant need to supply are the range, as with any other prior, and the expected tainting, θ0. We will see some practical applications of the methodology proposed about internal control evaluation in auditing.},

author = {Hernández Bastida, Agustín, Martel Escobar, María del C., Vázquez Polo, Francisco José},

journal = {Qüestiió},

keywords = {Inferencia bayesiana; Estimador de máxima verosimilitud; Antecedentes; maximum entropy prior; partial prior information; auditing},

language = {eng},

number = {2},

pages = {231-242},

title = {On maximum entropy priors and a most likely likelihood in auditing.},

url = {http://eudml.org/doc/40256},

volume = {22},

year = {1998},

}

TY - JOUR

AU - Hernández Bastida, Agustín

AU - Martel Escobar, María del C.

AU - Vázquez Polo, Francisco José

TI - On maximum entropy priors and a most likely likelihood in auditing.

JO - Qüestiió

PY - 1998

VL - 22

IS - 2

SP - 231

EP - 242

AB - There are two basic questions auditors and accountants must consider when developing test and estimation applications using Bayes' Theorem: What prior probability function should be used and what likelihood function should be used. In this paper we propose to use a maximum entropy prior probability function MEP with the most likely likelihood function MLL in the Quasi-Bayesian QB model introduced by McCray (1984). It is defined on an adequate parameter. Thus procedure only needs an expected value of θ0 known (in this paper the expected tainting) to obtain a MEP all an auditor or accountant need to supply are the range, as with any other prior, and the expected tainting, θ0. We will see some practical applications of the methodology proposed about internal control evaluation in auditing.

LA - eng

KW - Inferencia bayesiana; Estimador de máxima verosimilitud; Antecedentes; maximum entropy prior; partial prior information; auditing

UR - http://eudml.org/doc/40256

ER -