Priors in a Bayesian Audit: How Integration of Existing Information into the Prior Distribution Can Improve Audit Transparency and Efficiency

Abstract

Auditors often have prior information about the auditee before starting the substantive testing phase. For example, an auditor might have performed an audit last year, they might have information on certain controls in place, or they might have performed analytical procedures in an earlier stage of the audit. In this article, we show that applying Bayesian statistics in substantive testing allows for integration of this information into the statistical analysis through the prior distribution. This enables auditors to tailor their sampling procedure to the auditee, thereby increasing audit transparency, efficiency, and quality. However, defining a suitable prior distribution can be difficult because what constitutes a suitable prior depends on the specifics of the audit and the auditee. To help the auditor construct a prior distribution we discuss five methodologies, discuss their pros and cons, and give examples of how to apply them in practice.

The Bayesian Approach to Audit Evidence: Quantifying Statistical Evidence using the Bayes Factor

“…In audit sampling, the prior distribution can be used to incorporate existing evidence about the possible values of the misstatement into the sampling procedure (Corless 1972). For example, the auditor's risk assessments on the inherent risk and control risk are information that can be incorporated into the prior distribution (Derks et al 2021;Stewart 2013).…”

“…This implies that before seeing any data, 1 is much less likely than 0 . Note that in the case of the beta distribution, the and parameters can be interpreted as prior observations from a sample and can be adjusted to incorporate existing information on the occurrence of the hypotheses 1 and 0 (Derks et al 2021;Steele 1992).…”