A Comparative Analysis of the Bootstrap versus Traditional Statistical Procedures Applied to Digital Analysis Based on Benford's Law

摘要

This study develops a bootstrap procedure applied to digital analysis based on Benford's Law. It shows that the developed procedure provides accurate diagnoses of fraud as opposed to traditional statistical procedures. The traditional procedures such as the chi-square goodness-of-fit test exhibit the problem of excessive power as the volume of transactions becomes large. This problem may lead auditors to expend unnecessary fraud investigation costs. In contrast, applications of the proposed bootstrap procedure to reported annual earnings of S&P 1500 companies, Federal Election Commission data, and extremely fraudulent data demonstrate the robustness of the proposed procedure over different periods of time and across small or large financial data sets.