ISA 530

Audit Sampling

1Objective and scope

ISA 530 applies when the auditor has decided to use audit sampling in performing audit procedures. It deals with statistical and non-statistical sampling, the design and selection of the sample, performing tests of controls and tests of details on the sample, and evaluating the results. Sampling is one of the three means of selecting items for testing under ISA 500 (with selecting all items and selecting specific items); it is the only one whose results can be projected to the population. The standard complements ISA 500 and ISA 330 and does not address data analytics over the entire population, which is not sampling.

The objective is, when using audit sampling, to provide a reasonable basis for the auditor to draw conclusions about the population from which the sample is selected.

2Key definitions

3Requirements

Sample design, size and selection

• When designing a sample, consider the purpose of the procedure and the characteristics of the population, including what constitutes a misstatement or deviation, so that all and only the relevant conditions are captured. Define the population appropriately (an unrecorded-liabilities test samples subsequent payments, not the recorded payables list) and ensure it is complete.
• Determine a sample size sufficient to reduce sampling risk to an acceptably low level. Sample size increases with a lower acceptable sampling risk, a higher expected misstatement or deviation rate, a lower tolerable misstatement or rate, and a lower assurance from other procedures; it is virtually unaffected by population size except for very small populations. Stratification reduces sample size for a given level of assurance.
• Select items in such a way that each sampling unit in the population has a chance of selection: random selection (random number tables or generators), systematic selection (a fixed interval from a random start, provided the population is not patterned in a way that coincides with the interval), monetary unit sampling (value-weighted, giving larger items a proportionately higher chance), haphazard selection (without a structured technique but avoiding conscious bias; not for statistical sampling), and block selection (contiguous items, rarely appropriate as the sole method because populations are structured).

Performing the procedures

• Perform procedures appropriate to the purpose on each item selected. If the procedure is not applicable to the selected item (a voided cheque, a cancelled invoice), perform the procedure on a replacement item.
• If unable to apply the designed procedures or suitable alternative procedures to a selected item (the document cannot be found, the customer does not reply), treat that item as a deviation from the prescribed control (for tests of controls) or a misstatement (for tests of details). A missing item is not simply replaced.

Evaluating results

• Investigate the nature and cause of any deviations or misstatements identified, and evaluate their possible effect on the purpose of the procedure and on other areas of the audit (a deviation caused by a staff member on leave is different from one caused by a control being bypassed on instruction; a misstatement pattern by location or period may reveal a systematic cause).
• Where the auditor considers a misstatement or deviation an anomaly, obtain a high degree of certainty that it is not representative of the population by performing additional procedures, before excluding it from the projection.
• For tests of details, project misstatements found in the sample to the population (by ratio for a value-weighted sample, by average per unit for a unit sample, stratum by stratum where stratified) to obtain a broad view of the scale of misstatement; anomalous misstatements are excluded from projection but still added to the total. For tests of controls, no explicit projection is necessary since the sample deviation rate is also the projected rate for the population.
• Evaluate the results: whether the use of sampling has provided a reasonable basis for conclusions about the population. For tests of controls, an unexpectedly high deviation rate may increase the assessed risk of material misstatement unless further evidence is obtained. For tests of details, an unexpectedly high projected misstatement (plus anomalies), especially one approaching tolerable misstatement, may cause the auditor to conclude that the population is materially misstated, or may leave the auditor unable to conclude, in which case the auditor requests management to investigate and correct, or extends the sample, or performs other procedures.

4Documentation and reporting

The sampling working paper records the objective and the assertion, the population and its completeness check, the definition of a deviation or misstatement, the sampling method and the reasons for it, the parameters (tolerable and expected misstatement or deviation rate, confidence level, sample size), the identifying characteristics of the items selected (ISA 230), the procedures performed, each deviation or misstatement with its nature and cause, the treatment of any anomaly and the evidence for that treatment, the projection and its arithmetic, and the conclusion. Projected and known misstatements flow into the ISA 450 evaluation and, through it, into the opinion; deviations flow into the control risk reassessment under ISA 330 and, where they reveal deficiencies, into the ISA 265 communication. ISA 530 has no reporting requirement of its own.

5Examinable focus