Appendix FNonstatistical Sampling Plans

A sampling plan is nonstatistical when it fails to meet at least one of the criteria of a statistical sampling plan (Apostolou & Alleman, 1991a). Yet, there are similarities between the two types of plans. Both require judgment on the part of the analyst. Audit procedures will be the same for either type of plan, and both are permissible by the standards of the Institute of Internal Auditors (IIA, 2013). The major difference between them is that sampling risks cannot be measured in a nonstatistical sampling plan.

There are circumstances in which nonstatistical sampling is the more appropriate of the two. Nonstatistical sampling may be used when results are needed to confirm a condition, or when judgment is more important than random sampling, such as in reviewing records, searching for unusual relationships, or interviewing client personnel (Guy, 1981a). Nonstatistical sampling is also correct when there is no sampling—the entire lot is tested. This seems to be an oxymoron; a sampling procedure for a non‐sampled population. Yet, sampling plans bring a formality and direction necessary to any analysis. Consider that even if you intend ...

Get Forensic Systems Engineering now with the O’Reilly learning platform.

O’Reilly members experience live online training, plus books, videos, and digital content from nearly 200 publishers.