Sampling Risk - Sample Selection

Sample Selection

When selecting a sampling approach there are two approaches to audit sampling: non-statistical and statistical approach. Three ways that statistical sampling can assist the auditor are: to maximize the productivity with minimum wasted effort in designing the sample, to measure the sufficiency of the evidence taken during the audit, and to analyze the results. The statistical approach allows the auditor to measure the risk that is being sampled to help in reducing it to an acceptable level. With respect to performing samples, statistical sampling involves different kinds of costs such as training the auditors, designing individual samples to meet the requirements, and choosing the items to be examined. If there is insufficient audit evidence it is the responsibility of the auditor to choose between non statistical or the statistical sampling approaches considering their effectiveness and related costs.

Although exercising careful judgment is crucial during every step of the sampling process, it is extremely necessary when choosing the non-statistical approach. This method does not include the use of tables or statistical percentages, but rather it relies upon professional judgment on the part of the auditor as well as the policy implemented by the firm. Under this approach, it is common practice for most CPA firms to create universal guidelines for auditors in order to determine a proper sample size. For example, if a given client's control risk is high, a firm would typically require a high sample size when selecting records.

In order to successfully gather a sample, it is important to consider the collection as a whole and the relevance of the particular items. The most common successful method is to select an even amount of items which accurately represents the list as a whole. Selecting only large or small amounts could distort the sample which creates risk.