Dynamic analysis of Bayesian audit strategies with tests of controls and reliability modeling

Abstract

Purpose

The purpose of this paper is to summarize a simulation study that analyzed the performance of Bayesian audit strategies in a novel fashion – dynamically and with varying sample sizes depending on the extent of an auditor's prior information.

Design/methodology/approach

The prior information for the Bayesian strategies arises from a set of control tests that are evaluated making use of reliability theory. The entire audit strategy is simulated under systematically different control reliabilities and related amounts of total misstatements in an accounting population.

Findings

The major finding is that robust Bayesian audit strategies that have recently been developed in auditing research are more sensitive to non‐sampling errors than existing strategies of audit practice.

Practical implications

The authors find that there are differential effects of sampling error vs non‐sampling error on the Bayesian strategies and that controls testing does not need to be extensive to get full internal control reliance.

Originality/value

The paper adds to existing research by examining the performance of various Bayesian audit strategies under more realistic audit conditions of sampling and non‐sampling uncertainty.

Citation

Chen, W., Menzefricke, U. and Smieliauskas, W.J. (2011), "Dynamic analysis of Bayesian audit strategies with tests of controls and reliability modeling", Grey Systems: Theory and Application, Vol. 1 No. 3, pp. 216-227. https://doi.org/10.1108/20439371111181224