Sampling A sample is a subset of a population designed to represent the characteristics of that population. Samples are often used as a proxy for a population when calculating the characteristics of that population is too costly, too timely, or otherwise unfeasible. refers to examining less than 100% of a population and using the results to draw a general conclusion about the entire population. Sampling is used both in the test of controls and in the tests of details.

During the initial testing phase of an audit, the auditor performs tests of controls using attribute sampling A form of sampling that involves examining a sample of items from a population to determine what percentage of the items has a specific attribute. It is often used as a test of controls. to determine the operating effectiveness of controls on which they plan to rely. For example, if an entity requires credit approval on all customer orders, an auditor may test a sample of orders for evidence of approval.

During the substantive testing phase of the audit, the auditor uses variables sampling A technique applied to tests of details (eg, estimate an amount or the amount of a misstatement). to perform tests of details of transactions, accounts, and disclosures to obtain sufficient appropriate audit evidence to support management assertions. Explicit or implicit representations or claims made by management concerning the presentation of the entity's financial statements.

Sampling is not always appropriate for all parts of the audit. For example, sampling may not provide sufficient evidence of segregation of duties (Choice B). Examining organizational charts and observing employees performing their duties would probably be more efficient and effective.

(Choice C and D) Testing a sample of accounts receivable confirmations or budget center directors' allocation of annual budget to sales units uses variables sampling to test details, not controls.

Things to remember: Sampling refers to examining less than 100% of a population and using the results to draw a conclusion about the entire population. Sampling is used to test controls (ie, attribute sampling) and details (ie, variables sampling).