摘要：A central feature in the montage of executing the internal audit, in a non?forensic context, is a random sample of sufficient size to create the evidence needed to make the decision if extended investigative procedures are warranted or not. This is critical not only in maintaining a best practices profile for the department of internal auditing but also in “partnering” with the external auditors by assuring, insofar as possible, that the work of the internal audit group can be accepted as audit evidence by the external auditors and so conserving scarce organizational resources. In fact, this partnering is one of the long term goals of the PCAOB for controlling the cost of the external certification audit. However, a contentious issue in sampling is: How should the internal auditor ferret out those accounts that are likely candidates for discovery sampling? This is the point of departure of our paper where we present a simple and validated protocol based upon the digital frequency paradigm introduced by Newcomb & Benford and popularized in the audit context by Nigrini to identify accounts under audit that seem reasonable candidates for extended procedures discovery sampling testing.
