What question did this study set out to answer?

The study aims to develop Bayesian error bounds for overstated dollar amounts in accounting populations using prior information.

Multinomial-Dirichlet Bounds for Dollar-Unit Sampling in Auditing.

View Full Paper

Ask AI

Bookmark

Authors

Bayesian approach improves error bounds in accounting populations, suggesting efficient sampling methods.

The study aims to develop Bayesian error bounds for overstated dollar amounts in accounting populations using prior information.
Utilized a Bayesian approach with Dirichlet prior distributions.
Employed multinomial distribution models within the dollar-unit sampling framework.
Conducted simulation studies to assess the properties of the derived bounds.
Bayesian bounds demonstrated good properties in repeated sampling, maintaining significance levels close to the nominal level.
Comparison with traditional bounds showed improved tightness in many typical accounting populations.
Computational efficiency of the Bayesian approach was confirmed to be independent of sample size and error counts.

Tsui et al. (1985) studied this question.

View Full Paper

Ask AI

Bookmark