I.

Introduction
In auditing, collecting evidence is an essential and critical task. The sampling technique
has become a tool that enables auditors to perform this task effectively. Sampling allows
auditors to select a representative portion of the population to conclude the whole,
thereby saving time and costs in the audit process.

The significance of sampling lies not only in its convenience but also in its capacity to
assess risk. Examining the entire dataset is often unfeasible due to the substantial
workload and resource limitations. By employing sampling, auditors can concentrate on
the most critical segments, thereby enhancing the reliability of their findings.

Sampling also assists auditors in detecting potential errors or fraud while simultaneously
evaluating the effectiveness of internal control systems. This method not only ensures
that financial reports are accurate but also reinforces stakeholders' confidence in the
organization's transparency.

In this discussion, we will discover the concept of sampling, various methodologies, and
the key factors that need to be considered when designing and assessing samples in
auditing.
II. THE CONCEPT OF SAMPLING:

2.1 The Concept of Sampling

Assurance providers often use sampling rather than examining all available information
due to practicality. When done correctly, sampling can yield valid conclusions. According
to ISA (UK) 530, the objective of audit sampling is to provide a reasonable basis for
conclusions about the population from which the sample is taken.

Key Definitions:

 Audit Sampling: Applying audit procedures to less than 100% of a population,

where each sampling unit has a chance of selection to provide a reasonable basis for
conclusions about the entire population.
 Population: The entire set of data from which a sample is selected and conclusions
are drawn.

Not all testing procedures involve sampling. Examples include:

 Testing all items in a population (100% examination).

 Testing items with a specific characteristic.

100% examination might be suitable for substantive procedures if the population consists
of a few high-value items and there is a high risk of material misstatement.

Types of Sampling:

 Statistical Sampling: Characterized by random selection of items and using

probability theory to evaluate sample results, including measuring sampling risk.
 Non-Statistical Sampling: Lacks the characteristics of statistical sampling.
Auditors may select specific items based on their characteristics:

 High-value or key items.

 All items over a certain amount.
 Items to gather information about the client's business, transactions, or control
systems.

2.2 Design of the Sample

ISA 530 requires auditors to consider the audit procedure's purpose and the population
characteristics when designing a sample. This includes defining what constitutes a
deviation or misstatement and identifying the appropriate population for sampling.

Key Definitions:

 Misstatement: A difference between reported financial statement items and what is

required by the applicable financial reporting framework. Misstatements can result
from errors or fraud.
 Error: An unintentional misstatement, including omissions of amounts or
disclosures.

Auditors must ensure the sample population is appropriate and complete for audit
objectives. They must define the sampling unit to achieve an effective and efficient sample.

Examples of Sampling Units:

 Cheques listed on deposit slips.

 Credit entries on bank statements.
 Sales invoices.
 Receivables balances.
 A monetary unit.

ISA 530 requires each sampling unit in the population to have a chance of selection.
Auditors should use professional judgment to assess audit risk and design audit
procedures, ensuring the sample size reduces sampling risk to an acceptable level.

Key Definitions:

 Sampling Risk: The risk that the auditor’s conclusion based on a sample may differ
from the conclusion if the entire population were tested.
 Non-Sampling Risk: The risk of an erroneous conclusion for reasons unrelated to
sampling, such as inappropriate procedures or misinterpretation of evidence.

III. DESIGN OF THE SAMPLE:

3.1. Key Considerations:

When designing an audit sample under ISA 530, the auditor must:
  Define the specific purpose of the audit procedure and the characteristics of the population from
which the sample will be drawn.
 Consider the sampling and selection methods to align with the audit objective.
 Assess the nature of audit evidence to be obtained and potential conditions that may lead to
deviations or material misstatements.
 Clearly define what constitutes a deviation or misstatement and select the appropriate
population for sampling.
3.2. Factors influencing sample sizes:

ISA 530 gives examples of factors which influence sample sizes for tests of controls and tests of details:

a. Test of control
Factor Effect on Sample Size
An increase in the extent to which the auditor's risk assessment takes into
account relevant controls Increase
An increase in the tolerable rate of deviation Decrease
An increase in the expected rate of deviation of the population to be tested Increase
An increase in the auditor's desired level of assurance that the tolerable rate of deviation
is
not exceeded by the actual rate of deviation in the population Increase
An increase in the number of sampling units in the population Negligible effect

b. Test of details
Factor Effect on Sample Size
An increase in the auditor's assessment of the risk of material misstatement Increase
An increase in the use of other substantive procedures directed at the same assertion Decrease
An increase in the auditor's desired level of assurance that tolerable misstatement is
not exceeded by actual misstatement in the population Increase
An increase in tolerable misstatement Decrease
An increase in the amount of misstatement the auditor expects to find in the population Increase
Stratification of the population when appropriate Decrease
The number of sampling units in the population Negligible effect

Example: Hannah is planning to audit the accounts receivable of MCL Manufacturing LLC. (MCL).
MCL handles all sales transactions on a credit basis, and the company's accounts receivable ledger is
quite extensive. Sarah, on the other hand, classified this area as low risk because most customers pay their
bills on time and the controls for receivables and credit management are effective. Previous years' audits
showed very few errors. Therefore, she used a small sample size.
During the testing process, Sarah realized that the number of errors was significantly higher than she had
anticipated. As a result, she doubled the sample size and conducted additional tests.
Most auditing firms use computers.

Solution:
Hannah made the right choice because a larger sample size increases the possibility of finding
mistakes and offers a more trustworthy foundation for findings. Hannah should also reevaluate
the level of risk, perhaps reclassifying this area as medium or high risk, and add measures to her
audit procedures like utilizing balance confirmation procedures, testing the efficacy of internal
controls, and using data analytics to find anomalies in the ledger. Because of the intricacy of
MCL's accounts receivable ledger, using computer-assisted audit tools (CAATs) would make it
easier to identify anomalous transactions, compare data from the current year with data from
previous years, and choose audit samples more quickly. Lastly, Hannah should notify
management of any significant problems found and suggest actions such bolstering internal
controls, strictly observing credit policies, and debt more effectively. Finally, if Hannah finds
significant problems, she should inform management and suggest actions including tightening
internal controls, keeping a close eye on credit policies and debt collection, and reviewing the
ledger more frequently. This instance emphasizes the value of adaptable risk assessment that
changes in response to audit findings

IV. Sampling methods

4.1. Statistical Sampling:
- Statistical Sampling: An approach to sampling that has the following characteristics:
(a) random selection of the sample items;
(b) the use of probability theory to evaluate sample results, including measurement
of sampling risk.
- Types of Statistical Sampling:
 Simple Random Sampling: Random selection ensures that all items in the
population have an equal chance of selection, e.g., by using random number tables
or computerized generators.
 Systematic Sampling: Systematic selection involves selecting items using a
constant interval between selections, the first interval having a random start. When
using systematic selection, assurance providers must ensure that the population is
not structured in such a manner that the sampling interval corresponds with a
particular pattern in the population.
 Stratified Sampling: This is the method by which the sample units are selected
when the whole has been divided into groups according to the criteria directly
related to the research purpose. The selection of units from the nests is carried out
by the random selection method.
 Cluster Sampling: This is a method of organizing sample selection, in which the
number of sample units selected is not single but simultaneously selects a block of
units.
 Monetary Unit Sampling (MUS): This is a selection method that ensures that
every £1 in a population has an equal chance of being selected for testing. The
advantages of this selection method are that it is easy when computers are used,
and that every material item will automatically be sampled. Disadvantages include
the fact that if computers are not used, it can be time-consuming to pick the
sample, and MUS does not cope well with errors of understatement (as the
computer cannot select a f which is not there) or negative balances.
→ MUS is popular in auditing because it focuses on larger items that have the potential
to lead to material misstatements. The sample is selected based on monetary value, with
items of greater value having a higher probability of being selected. Systematic Sampling
is often used in audits when transactions are sequenced (such as invoices or documents).
Stratified Sampling is used when it is necessary to ensure representation from different
groups in the population, especially when items are of a heterogeneous nature. Simple
Random Sampling is less popular in auditing because it does not prioritize high-value or
high-risk items. However, it can be used when the population is small or homogeneous.
Cluster Sampling is rarely used in auditing, mainly when the population is dispersed or
the cost of direct sampling is high.
In my opinion, Monetary Unit Sampling (MUS) is considered the most popular in
auditing because:
- Focus on important high-value items.
- Effective in detecting material errors, especially in financial statement audits.
- Monetary Unit Sampling (MUS) is the preferred choice in financial statement audits.
Methods such as Systematic Sampling and Stratified Sampling are often used
additionally to ensure testing of small groups or the entire population.
 Example: An auditor examines accounts receivable with a total value of $10
million, including 1,000 transactions. Instead of randomly selecting transactions,
auditors use the MUS method, focusing on high-value transactions (for example,
transactions of $100,000 or more) to ensure detection of potential misstatements.
the ability to materially affect the financial statements.

4.2. Non-Statistical Sampling:

 Non-Statistical Sampling: A sampling approach that does not have characteristics
(a) and (b) is considered non-statistical sampling.
- Types of Non-Statistical Sampling:
 Haphazard Sampling: Haphazard selection may be an alternative to random
selection provided assurance providers are satisfied that the sample is
representative of the entire population. This method requires care to guard against
making a biased selection, for example towards items that are easily located, as
they may not be representative. It should not be used if assurance providers are
carrying out statistical sampling.
 Sequence or block selection: Sequence sampling may be used to check whether
certain items have particular characteristics. Sequence sampling may, however,
produce samples that are not representative of the population as a whole,
particularly if misstatements only occurred during a certain part of the period, and
hence the misstatements found cannot be projected onto the rest of the population.
 Judgmental Sampling: This is a method in which the interviewer is the one who
makes his judgment about the object to be selected in the sample. Thus, the
representativeness of the sample depends a lot on the experience and
understanding of the survey organizer and the data collector. For example,
interviewers are required to go to shopping malls to choose luxuriously dressed
women for interviews. Thus, there is no specific standard of "what is luxury" but
completely based on judgment in choosing the person to interview.
→ In my opinion, Judgmental Sampling is the most popular because Judgmental
Sampling is used by auditors based on experience and expertise to select samples from
potential material misstatement items or focus areas of the audit. Block Selection is often
applied when there is a need to save time or when transactions are organized into logical
blocks (for example, by day, month, or branch). However, this method runs the risk of
missing errors if the blocks are not representative of the population. And the haphazard
sampling method lacks systematicity and depends on the "randomness" of the auditor.
Bias can easily occur because sample selection can be influenced by intuition or personal
habits.
 Example: In a financial statement audit, the auditor wants to examine the
inventory of a manufacturing company. Instead of random selection, they focus on
testing high-value products or goods with a high risk of defects (like perishable
materials). The auditor believes that these items have a high risk of misstatement
and could have a material impact on the financial statements.

V. Evaluating and Concluding on the Sample Result:

5.1. Evaluating Sample Results

Once the auditor has drawn a sample and performed testing, the next step is to evaluate the
results. This involves comparing the sample findings to established criteria, typically the
tolerable misstatement or deviation rate. Here’s a breakdown of key considerations:

- Tolerable Misstatement (TM)

o Definition: The maximum amount of misstatement or error in a financial

statement that the auditor is willing to accept without affecting the audit opinion.
o Purpose: If the sample results show misstatements greater than the tolerable
level, the auditor will need to adjust their conclusions. This is crucial for ensuring
that the financial statements are free of material misstatements.
o Process: After testing the sample, the auditor calculates the error rate or
misstatement in the sample, then extrapolates these findings to the entire
population to estimate the total potential misstatement.
 If the sample misstatements exceed the tolerable misstatement for the
entire population, it indicates a potential material misstatement in the
financial statements.

- Evaluating the Errors

o Error Type: Errors can arise due to mistakes or fraud. An auditor must
differentiate between types of misstatements (e.g., unintentional errors vs.
deliberate misstatements) as they could influence the audit approach and
conclusion.
 o Extrapolating Results: Once errors are identified in the sample, auditors often
extrapolate the results to the entire population (for example, if a sample of 30
transactions shows 2 errors, extrapolation may suggest a similar error rate in the
remaining population). This extrapolation helps the auditor estimate the level of
risk in the population.

- Assessment of Sample Size and Risk

o Sample Size: A larger sample size generally leads to more reliable results, as it
reduces the risk of errors or misstatements going undetected. If the sample is
small or not representative, the risk of drawing incorrect conclusions increases.
o Risk Considerations: The auditor assesses whether the sample was appropriately
sized given the risk of material misstatement and the nature of the audit test. If
there is high inherent risk (i.e., the likelihood of misstatements occurring is high),
a larger sample size may be required.

- Risk of Incorrect Acceptance or Rejection

o Incorrect Acceptance: This occurs when the sample leads the auditor to
incorrectly conclude that there is no material misstatement when, in fact, there is
one. This risk is mitigated by careful sample design and evaluation.
o Incorrect Rejection: This occurs when the auditor concludes that a material
misstatement exists when it does not. This risk can be reduced by using statistical
sampling techniques and ensuring that the sample is representative of the
population.

5.2. Drawing Conclusions Based on the Sample

After testing a sample of goods, auditors need to make inferences from the sample.
By evaluating a sample taken from the complete population, audit sampling aims to
make it possible to draw conclusions from the full population.
The auditors must first determine if the items in question are actual misstatements
according to their pre-test definition. For instance, a sampling misposting between
customer accounts during receivables testing will not have an impact on the
auditors' conclusion that the total receivables value is accurate and fair.
The auditor must carry out the process on a substitute item if the anticipated audit
evidence pertaining to a particular sample item is not discovered. The item is not
regarded as a misrepresentation under these circumstances.
The qualitative aspects of misstatements are also considered, including the nature and cause of
the misstatement. The potential impact of the mistake on other aspects of the audit, such as the
overall impact on the financial statements and the auditors' evaluation of the accounting and
internal control systems, must also be taken into account.
When common characteristics are found in misstatements, the auditors may choose to create a
sub-population by identifying every item in the population that has the characteristic (such as
location). Then, auditing practices might be expanded in this domain.
The auditor may occasionally determine that the misrepresentation is an anomaly.
(Anomaly: A misstatement or deviation that is demonstrably not representative of
misstatements or deviations in a population.

To be considered anomalous, the auditors have to be certain that the misstatements

are not representative of the population. Extra work will be required to prove that a
misstatement is an anomaly.)

- Material Misstatement Evaluation

o If the sample results suggest that the misstatement is below the tolerable level,
the auditor can conclude that the financial statements are fairly presented,
assuming no other issues are identified during the audit.
o If the misstatement exceeds the tolerable level, the auditor may need to perform
additional testing, increase the sample size, or adjust their opinion on the financial
statements.
 This may lead to a qualified opinion or adverse opinion, depending on
the severity and pervasiveness of the misstatement.

- Actions if Errors Exceed Tolerable Misstatement

o Expand Testing: If the initial sample results are concerning, the auditor may
expand the testing or perform further procedures to obtain additional evidence.
This is often called "additional substantive testing."
o Adjust Financial Statements: If a material misstatement is confirmed, the
auditor may request the client to adjust the financial statements before the final
audit opinion is issued.
o Audit Opinion Impact: If the errors cannot be sufficiently addressed through
expanded testing or adjustments, the auditor may issue a modified opinion.

- Use of Statistical and Non-Statistical Approaches in Drawing Conclusions

o Statistical Sampling: In statistical sampling, the results are often analyzed using
probability theory. This provides a clear, quantifiable way of evaluating the
likelihood of errors and making conclusions based on that risk. Auditors use
confidence intervals and error rates to assess how the sample's findings relate to
the population.
o Non-Statistical Sampling: With non-statistical sampling, conclusions are often
drawn based on auditor judgment, which can introduce more subjectivity into the
conclusions. However, the auditor must still consider the overall risk of material
misstatement.

- Documenting the Conclusion

o Audit Evidence: The auditor must document the sampling process, including the
rationale for sample size, method, and any conclusions drawn. This
 documentation serves as evidence of the auditor's approach and is important for
the audit file and future reviews.
o Conclusion Reporting: Based on the sample results, the auditor will compile a
summary of the findings, explaining how the sample’s findings impact the
financial statements.

- Example:
Adrian carried out a supplier statement reconciliation on Peabody Ltd, testing the
completeness and valuation assertions. This means that he compared the statements
sent by suppliers to Peabody Ltd with the details on Peabody's own payables ledger.
Tolerable misstatement has been set at £10,000. The sample was 10 payables ledger
balances totalling £35,024 out of a total of £375,297. Adrian found that of these, eight
reconciliations proved that the balance on the ledger was correct, one showed that an
invoice had been misposted to a different supplier's account and one showed that an
invoice had not been posted at all.

Solution:
When considering the results of his sample, Adrian decided that he can disregard the
misposting, as, although it means that two accounts were individually misstated, the
overall balance was not affected by this mistake. In the case of the invoice that had
simply been omitted in error however, Adrian had to conclude that this misstatement of
£250, which does affect the overall total balance, could be repeated in the overall
population with the potential for causing material misstatement. Adrian projected the
total population misstatement based on the sample and compared the outcome with
tolerable misstatement. In this case he found that the projected misstatement of £2,679
was considerably below the tolerable misstatement of £10,000 and concluded that no
further action was required. He concluded from his testing that the trade payables
balance in the financial statements was fairly stated.

VI. Conclusion

REFERENCE
1. Assurance study manual 2019 Book
2. https://vietnambiz.vn/chon-mau-phan-to-stratified-sampling-trong-thong-ke-la-gi-
20191118162713778.htm
3. https://vietnambiz.vn/chon-mau-ca-khoi-cluster-sampling-trong-thong-ke-la-gi-
20191118165052043.htm
4. https://vietnambiz.vn/chon-mau-phi-ngau-nhien-non-probability-sampling-trong-
thong-ke-la-gi-20191118171806571.htm