Corporate Accounting and Auditing · Audit Sampling, Audit Techniques and Analytical Procedure

Audit Sampling: Meaning and Concepts under SA 530

Q: What is audit sampling under SA 530?

It is the application of audit procedures to less than 100% of items in a population of audit relevance, such that all sampling units have a chance of selection. The aim is a reasonable basis to draw conclusions about the entire population.

Q: What is the difference between sampling risk and non-sampling risk?

Sampling risk is the risk that the conclusion from a sample differs from the conclusion if the whole population were tested. Non-sampling risk is the risk of a wrong conclusion for any reason not related to sampling, such as inappropriate procedures or misinterpreting evidence.

Q: What is tolerable misstatement in audit sampling?

It is a monetary amount set by the auditor for which the auditor seeks assurance that actual misstatement in the population does not exceed it. It is performance materiality applied to a sampling procedure and may be equal to or lower than performance materiality.

Q: Does population size affect sample size?

For large populations, the actual size has little, if any, effect on sample size. For small populations, sampling may not be as efficient as other ways of getting sufficient appropriate audit evidence.

Updated 10 October 2026 · Fact-checked

Audit sampling means applying audit procedures to less than 100% of the items in a population, so that every item has a chance of selection, and then drawing conclusions about the whole population. SA 530 defines the key terms. To solve questions, identify the population, the purpose, the risk type and the tolerable limit.

Understand Audit Sampling: Meaning and Concepts

An auditor cannot check every voucher, invoice or control operation. So the auditor tests a part and reaches a conclusion about the whole. SA 530 calls this audit sampling: applying audit procedures to less than 100% of items in a population of audit relevance, such that all sampling units have a chance of selection, to give a reasonable basis for conclusions about the entire population.

The population is the entire set of data from which the sample is selected and about which the auditor wants to conclude. A sampling unit is an individual item making up the population. For example, if you test sales invoices of a year, the population is all sales invoices of that year and each invoice is a sampling unit. The auditor must also obtain evidence that the population is complete.

Sampling can go wrong in two ways. Sampling risk is the risk that the conclusion based on a sample differs from the conclusion if the whole population were tested. It has two forms. In a test of controls, the auditor may conclude controls are more effective than they are. In a test of details, the auditor may conclude that no material misstatement exists when it does. This is the main worry because it hurts audit effectiveness and can lead to a wrong opinion. The opposite error (controls less effective than they are, or a misstatement that does not exist) only affects efficiency, as it leads to extra work.

Non-sampling risk is the risk of a wrong conclusion for any reason not related to sampling. Examples in SA 530 include using inappropriate audit procedures, misinterpreting audit evidence, and failing to recognise a misstatement or deviation. Testing 100% of items does not remove it.

Tolerable misstatement is a monetary amount set by the auditor, for which the auditor seeks an appropriate level of assurance that actual misstatement in the population does not exceed it. It is performance materiality (SA 320) applied to a particular sampling procedure, and it may be the same as or lower than performance materiality. For controls, the matching idea is the tolerable rate of deviation. An anomaly is a misstatement or deviation demonstrably not representative of the population. Stratification divides the population into sub-populations with similar characteristics, often monetary value. Statistical sampling needs both random selection and probability theory to evaluate results; otherwise it is non-statistical.

Key rules to remember

Audit sampling: Procedures on < 100% of items, with every sampling unit having a chance of selection; Purpose: a reasonable basis for conclusions about the whole population (SA 530, para 5(a)).
Statistical sampling: Random selection + probability theory to evaluate results; If either feature is missing, it is non-statistical sampling.
Evaluation of tests of details: Projected misstatement + anomalous misstatement (if any) compared with tolerable misstatement; If the total exceeds tolerable misstatement, the sample does not give a reasonable basis for conclusions about the population. The closer it is to tolerable misstatement, the more likely actual misstatement exceeds it (para A22).
Tolerable misstatement: Tolerable misstatement ≤ performance materiality; It may be equal to or lower than performance materiality (para A3).
Sample size factors (tests of details): Increase: assessed risk of material misstatement, desired assurance, expected misstatement. Decrease: tolerable misstatement, other substantive procedures on the same assertion, stratification. Population size: negligible effect; From Appendix 3. For large populations, size has little effect.
Sample size factors (tests of controls): Increase: reliance on controls, expected deviation rate, desired assurance. Decrease: tolerable deviation rate. Population size: negligible effect; From Appendix 2.

How to solve Audit Sampling: Meaning and Concepts questions

Use this method for theory or scenario questions on sampling concepts.

1Identify the purpose of the test: test of controls or test of details.
2Define the population and the sampling unit clearly, and confirm the population is complete.
3Name the risk in the scenario: sampling risk (conclusion differs from testing everything) or non-sampling risk (wrong procedure, misread evidence, missed error).
4If sampling risk, state which type: the dangerous one (over-reliance or missing a material misstatement) or the efficiency one.
5For monetary questions, compare projected misstatement plus anomalous misstatement with tolerable misstatement.
6State the conclusion and the auditor's response, such as extending testing or obtaining other evidence.
7Quote the SA 530 term in your answer to earn definition marks.

Quickest way: Risk-label shortcut

When to use it: Use in MCQs asking you to classify a risk or a term.

Ask: would testing every item have avoided this error? If yes, it is sampling risk.
If the error would remain even with 100% testing (wrong procedure, misreading evidence), it is non-sampling risk.
For direction, ask: did the auditor wrongly trust the client? That is the effectiveness risk. Did the auditor wrongly doubt the client? That is the efficiency risk.
For sample size, remember that higher risk or higher assurance means bigger samples, and higher tolerable limits mean smaller samples.

Common mistakes in Audit Sampling: Meaning and Concepts

Saying sampling means testing a random selection only
Students confuse sampling with statistical sampling.
Fix: Random selection is needed for statistical sampling only. Audit sampling requires that every unit has a chance of selection. Non-statistical sampling is also valid sampling.
Treating non-sampling risk as controllable by a bigger sample
Students link all errors with sample size.
Fix: Non-sampling risk comes from inappropriate procedures, misinterpreting evidence or failing to recognise errors. Training, supervision and good procedures reduce it, not a larger sample.
Mixing up the two kinds of sampling risk
Both are described as a wrong conclusion.
Fix: Remember that concluding controls are more effective, or that no material misstatement exists, is the effectiveness risk. The opposite affects efficiency only.
Treating tolerable misstatement as the same as materiality
Both are monetary limits.
Fix: Tolerable misstatement is performance materiality applied to a sampling procedure. It may be equal to or lower than performance materiality.
Saying a larger population always needs a larger sample
It sounds logical.
Fix: For large populations, size has little, if any, effect on sample size. Risk, tolerable limit, expected error and assurance matter more.
Ignoring anomalies when projecting errors
Students project every error found.
Fix: An anomaly is demonstrably not representative, so the auditor gets a high degree of certainty about that. The auditor adds anomalous misstatement to projected misstatement when evaluating, as SA 530 para A22 states.

Worked examples

Example 1

During the audit of Sundaram Textiles Ltd, the auditor tests 60 purchase invoices but wrongly applies a procedure that does not address the assertion. As a result a misstatement in the sample is not recognised. Identify the risk and explain if a larger sample would help.

Show the solution

The error arose from an inappropriate procedure and failure to recognise a misstatement.
SA 530 lists these as examples of non-sampling risk.
The error is not caused by testing only part of the population, so it would recur even with 100% testing.
A larger sample using the same flawed procedure would not fix it.

Answer: It is non-sampling risk. A larger sample does not help; the auditor should use appropriate procedures, supervise and review the work to recognise misstatements.

Example 2

Tolerable misstatement for trade receivables of Kaveri Foods Ltd is ₹5,00,000. The sample shows a projected misstatement of ₹4,60,000 and an anomalous misstatement of ₹60,000. What should the auditor conclude?

Show the solution

Best estimate of misstatement = projected misstatement + anomalous misstatement.
= ₹4,60,000 + ₹60,000 = ₹5,20,000.
Compare with tolerable misstatement of ₹5,00,000.
₹5,20,000 exceeds ₹5,00,000.

Answer: The total of ₹5,20,000 exceeds tolerable misstatement of ₹5,00,000, so the sample does not provide a reasonable basis for conclusions about the population. The auditor should obtain additional audit evidence or extend testing.

Exam tips

Learn the SA 530 definitions word for word in your own plain phrasing; short notes questions reward them.
For sampling risk versus non-sampling risk, give a definition, two examples each and one line on whether sample size affects it.
In sums, show the line: projected plus anomalous misstatement versus tolerable misstatement, then state the conclusion.
Remember the direction of each sample-size factor; MCQs often ask whether a factor increases or decreases sample size.
There is no negative marking in Section A, so attempt every MCQ.

Practice questions from Audit Sampling, Audit Techniques and Analytical Procedure

Audit Sampling: Meaning and Concepts in other exams

The same ground in other exams, if you are preparing for more than one or want another angle on it.

Audit Sampling: Meaning and Concepts: frequently asked questions

What is audit sampling under SA 530?

It is the application of audit procedures to less than 100% of items in a population of audit relevance, such that all sampling units have a chance of selection. The aim is a reasonable basis to draw conclusions about the entire population.

What is the difference between sampling risk and non-sampling risk?

Sampling risk is the risk that the conclusion from a sample differs from the conclusion if the whole population were tested. Non-sampling risk is the risk of a wrong conclusion for any reason not related to sampling, such as inappropriate procedures or misinterpreting evidence.

What is tolerable misstatement in audit sampling?

It is a monetary amount set by the auditor for which the auditor seeks assurance that actual misstatement in the population does not exceed it. It is performance materiality applied to a sampling procedure and may be equal to or lower than performance materiality.

Does population size affect sample size?

For large populations, the actual size has little, if any, effect on sample size. For small populations, sampling may not be as efficient as other ways of getting sufficient appropriate audit evidence.