AUDIT SAMPLING –ISA 530

1. MEANING
Audit sampling: the application of audit procedures to less than 100% of items within a population of
audit relevance such that all sampling units have a chance of selection, in order to provide the
auditor with a reasonable basis on which to draw conclusions about the entire population.

2. THE NEED FOR SAMPLING

1. Prohibitive costs
To apply audit procedures, costs have to be incurred, e.g. salaries to the staff conducting the
audit. It will usually be very expensive to test every item in any large accounting population.
In the above example, the cost of verifying all sales invoices would be prohibitively high.

2. Time constraint
Not only costs, but also the time spent in verification is substantial if the volume is large.
There are time constraints on the completion of audit. Sampling saves time while retaining
the confidence level.

3. Reasonable assurance
An audit gives reasonable assurance and not absolute assurance about the assertions
contained in the financial statements. It is not necessary to verify the entire population in
order to obtain reasonable assurance.

3. WHEN IS SAMPLING INAPPROPRIATE

Sampling may not always be appropriate. If a population contains a low number of high value items,
and other means do not provide sufficient appropriate evidence, it may be more appropriate to carry
out a 100% examination. For example, if the addition of non-current assets contains only 10 invoices
of high value. It will be appropriate to apply audit procedures to each of the purchases.

4. METHODS OF SELECTING SAMPLE

Two types of audit sampling:
(a) Statistical sampling – uses the laws of probability to select and evaluate the results of
an audit sample, therefore, the sampling risk is quantified for drawing the conclusion
about the population.

(b) Non-statistical sampling (judgment sampling) – the auditor considers sampling risk
without using law of probability to measure it.

Selection methods for statistical sampling:

(a) Random sample selection
Ensures that all items in the population have an equal chance of selection, e.g. by use of
random number tables or computerized generator.

1 | Shwaibu Sella (CPA,MSc,BBA,ATEC) +255784397398

 (b) Systematic sample selection
involves selecting items using a constant interval (e.g. every nth item) between
selections, the first interval having a random start.
(c) Stratified sample selection
The objective of stratification is to reduce the variability of items within each stratum
and therefore allows sample size to be reduced without increasing sampling risk.
The population is divided into different strata, each of which has similar characteristic,
then sampling techniques such as the random selection method can be applied in each
stratum.

Example:
Stratum Composition of stratum No. of accounts (method
of selection used)
1. Accounts of TZS 10,000 or over All accounts
2. Accounts of TZS 5,000 to TZS 9,999.99 50 accounts (random
number)
3. Accounts of less than TZS 5,000 30 accounts (random
number)

(d) Monetary unit sampling

This method of sampling aims to ascertain the accuracy of financial accounts. The
sample size selection and evaluation is in monetary terms, wherein monetary amounts
are converted into units. For example a payable balance of TZS30,000 contains 30,000
sampling units. This method is generally used in testing internal controls.

4.3 Selection methods for non-statistical sampling:

(a) Directed sample selection
The selection of each item based on some judgmental criteria by the auditor. The
criteria used may include:
(i) items most likely to contain misstatements;
(ii) items containing selected population characteristics;
(iii) large dollar coverage.

(b) Block (or sequence) sample selection

Is the selection of several items in sequence. Once the first item in the block is
selected, the remainder of the block is chosen automatically. For example an auditor
may use a sample of 50 consecutive cheques to check whether cheques are signed
by authorized signatories rather than picking 50 single cheques throughout the year.

Sequence sampling may however produce samples that are not representative of
the population as a whole, particularly if errors only occurred during a certain part of
the period, and hence the errors found cannot be projected onto the rest of the
population.

Nevertheless, block sampling can result in significant cost savings in audit time, and
2 | Shwaibu Sella (CPA,MSc,BBA,ATEC) +255784397398
 there are some occasions where practical considerations may require the use of
block sampling, for example when visiting a branch.

(c) Haphazard sample selection

Under this method, sample items are selected arbitrarily, usually by manual choice.
The objective of this selection process is that all items in the population have an
equal chance of being represented in the sample. Therefore the selection process
must be unbiased (i.e. the auditor must not deliberately avoid certain items) and free
from predictability.

5. STEPS OF AUDIT SAMPLING

The steps of audit sampling involve the following:
(a) Design the sample:
Auditor should consider the specific audit objectives, the nature of the population
from which samples are selected and the sample size when designing an audit
sample.

(b) Selection of sample:

Auditor should select sample items that are the representative of the population in
respect of characteristics being tested.

For example, the auditor selects specific monetary units from within the accounts
receivable balances, the audit effort is directed to the larger value items because
they have a greater chance of selection and can reduce the sample size.

Ideally, the auditor should select items for the sample that all sampling units in the
population have a chance of being selected.

(c) Evaluation of sample results:

After the appropriate audit procedures have been applied on the samples, the
auditor should analyse the errors in the sample and draw conclusions for the
population as a whole.

6. SELECTING REPRESENTATIVE SAMPLE

The characteristics of a representative sample are that the audit interest of the sample is
approximately the same as that of the population.

Causes of selecting non-representative samples

Definition
Sampling risks – It is an inherent part of sampling that results from testing less than the
entire population. Sampling risk arises from the possibility that the auditor’s
conclusion, based on a sample, may be different from that generated from the entire
population.

3 | Shwaibu Sella (CPA,MSc,BBA,ATEC) +255784397398

 The way to control the sampling risk may include:
(a) Increasing the sample size will reduce sampling risk.
(b) Using an appropriate sampling method will reasonably assure representativeness.

Types of Sampling Risk

(a) Tests of control
(i) Risk of under reliance– this is the risk that the assessed level of control risk
based on the sample is greater than the actual compliance rate of the control.
(ii) Risks of over reliance – this is the risk that the assessed level of control risk
based on the sample is less than the actual compliance rate of the control.
(b) Substantive procedures
(i) Risk of incorrect rejection– this is the risk that the sample supports the
conclusion that the recorded transaction or account balance is materially
misstated when, in fact, it is not materially misstated.
(ii) Risk of incorrect acceptance– this is the risk that the sample supports the
conclusion that the recorded transaction or account balance is not materially
misstated when, in fact, it is materially misstated.

Alternative names used

(i) Over-optimism:
Risk that an auditor will give POSITIVE conclusion based on sample instead of
NEGATIVE conclusion if the entire population was put in the same test.
The risk that the auditor will conclude:
 In the case of controls, that they are more effective than they actually are
 In the case of test of details, that material error does not exist when in fact it
does

This risk affects the effectiveness of an audit, leading to an inappropriate audit

opinion.

(ii) Over-pessimism:
Risk that an auditor will give NEGATIVE conclusion based on sample instead of
POSITIVE conclusion if the entire population was put in the same test.
The risk that the auditor will conclude:

 In the case of controls, that they are less effective than they
actually are
 In the case of test of details, that material error exists when in fact it does not

7. THE ROLE OF SAMPLING IN OBTAINING AUDIT EVIDENCE

Audit evidence is obtained by performing:

1. Risk assessment procedures
Usually, sampling will not be used in risk assessment procedures. Understanding an entity and its
environment requires professional skills and is not suitable for sampling.

4 | Shwaibu Sella (CPA,MSc,BBA,ATEC) +255784397398

 2. Tests of controls
Audit sampling for tests of controls is generally appropriate. However, non-statistical sampling
may be more appropriate than statistical sampling for tests of controls because the auditor can
use judgment to choose items where controls might not operate as well. For example, when a
supervisor has been off work with illness, evidence that the controls have operated must be
available.

3. Substantive procedures
Substantive procedures consist of tests of details and analytical procedures. Audit sampling relates
only to tests of details and not to analytical procedures. In connection with tests of details,
sampling can be applied to:
(a) Verify one or more assertions about a financial statement assertion. For example, to test
the existence of payables, letters are sent to the suppliers in a sample.
(b) Make an independent estimate of some amount. For example, estimation of the value
of obsolete inventories

8. FACTORS INFLUENCING SAMPLE SIZE

1. Effectiveness of Internal Controls
If the risk of material misstatement is reduced by the operating effectiveness of controls
For example, good controls on purchases where each purchase order is authorised by
the purchase manager, goods are inspected by the quality control officer and received by
the store keeper reduce a chance of material misstatement.

2. Tolerable rate of deviation

The maximum error in a population that the auditor is willing to accept. An increase in the
rate of deviation from the prescribed control activity that the auditor expects to find in the
population. If the auditor expects that the deviations from control activity would be higher
(but they do not accept them), then they would increase the sample size.

3. Use of other substantive procedures

An increase in the use of other substantive procedures directed at the same assertion.

4. Auditors desired level of assurance

An increase in the auditor’s desired level of assurance that tolerable misstatement is not
exceeded by actual misstatement in the population.

5. Expected level of risk of material misstatement

An increase in the auditor’s assessment of the risk of material misstatement. For example, if
the auditor assesses that the risk of material misstatement has increased, they would
increase the sample size (or also apply other procedures).

6. Stratification of the population.

For example, if the payables are stratified according to values, they become more uniform,
and therefore smaller samples are possible.

5 | Shwaibu Sella (CPA,MSc,BBA,ATEC) +255784397398

CLASS REVISION QUESTIONS
Question One
The audit assistant deputed to audit a small enterprise, in a meeting for planning the audit, insists
that for a small unit there is no scope for audit sampling. Do you agree?

Question Two
You are to audit tangible non-current assets. Explain which of the audit procedures are open to the
sampling process.

Question Three
In connection with the audit of payables, explain how different factors would increase or decrease
the size of a sample, for tests of control and tests of details.

Question Four
(a)
(i) In the context of ISA 530 Audit Sampling and Other Means of Testing, explain and provide
examples of the terms ‘sampling risk’ and ‘non-sampling’ risk.
(ii) Briefly explain how sampling and non-sampling risk can be controlled by the audit firm.

(b) Tam Co is owned and managed by two brothers with equal shareholdings. The company
specializes in the sale of expensive motor vehicles. Annual revenue is in the region of TZS70,000
million and the company requires an audit under local legislation.

About 500 cars are sold each year, with an average value of TZS140 million, although the range
of values is from TZS130 million to TZS160 million. Invoices are completed manually with one
director signing all invoices to confirm the sales value is correct. All accounting and financial
statement preparation I s carried out by the directors. A recent expansion of the company’s
showroom was financed by a bank loan, repayable over the next five years.

The audit manager is starting to plan the audit of Tam Co. The audit senior and audit junior
assigned to the audit are helping the manager as a training exercise.

Comments are being made about how to select a sample of sales invoices for testing. Audit
procedures are needed to ensure that the managing director has signed them, and then to trace
details into the sales day book and sales ledger.
‘We should check all invoices’ suggests the audit manager.
‘How about selecting a sample using statistical sampling techniques?’ adds the audit senior.
‘Why waste time obtaining a sample?’ asks the audit junior. He adds ‘taking a random sample of
invoices by reviewing the invoice file and manually choosing a few important invoices will be
much quicker.’

REQUIRED:
Briefly explain each of the sample selection methods suggested by the audit manager, audit
senior and audit junior, and discuss whether or not they are appropriate for obtaining a
representative sample of sales invoices.

6 | Shwaibu Sella (CPA,MSc,BBA,ATEC) +255784397398

Question Four

ISA 530 explains about the audit sampling and other selected test procedures. The standards apply
to statistical and non-statistical sampling methods and provide practical guidance on such matters as
sampling risks, stratification and selection methods.

REQUIRED:
What are the main advantages that can be derived by the auditor from the successful employment of
the statistical sampling techniques, as opposed to non-statistical sampling? (10 marks)
(Total: 20marks)
Question Six
(a) You are the audit manager on a client where an annual sale is TZS. 640 million.
During the course of annual audit the following table was developed by an audit team
member, to categorize the annual sales
TZS.
Category A 50 sales transactions to different customers 300 million
Category B 100 transactions to different customers 200 million
Category C 500 transactions to different customers 140 million
Total 640 million

Sohail, a team member, is of the view that if verification of all the transactions in category A is
carried out, there is no need to perform further procedures. However, other team members do
not agree and consider that proper sampling should be carried out from the total population and
categorization should be ignored.
REQUIRED: As an audit manager of the job, you are required to:
(i) Explain how audit efficiency could be improved by using the above table.
(ii) List other ways in which the sales population may be categorized and what precaution
should be taken while carrying out such categorization.
(iii) Give your opinion on the views expressed by: Sohail Other audit team members.
(11 marks)
(b) Describe the circumstances in which an auditor may decide to examine entire population of
items that make up an account balance.(3 marks)
(Total: 14 marks)

Question Seven

(a) Differentiate between the following:

(i) Statistical and non-statistical sampling
(ii) Sampling and non-sampling risk (5 marks)
(b) You are the audit manager on Apple Distribution Limited (ADL). While reviewing the audit
planning documentation, you found that the audit team has selected
100 out of a total of 2,550 debtors for balance confirmation. The details are as follows:
 50 largest debtors constitute approximately 40% of total debtors. Out of these, 10
have been selected.
 90 other debtors were selected through haphazard sampling.
7 | Shwaibu Sella (CPA,MSc,BBA,ATEC) +255784397398
  All debtors below TZS. 5,000 were ignored as immaterial.
 Balances due from government and some of the related parties were ignored as
prior years working papers showed that they never responded to requests for
confirmation.
REQUIRED:
(i) Comment on the sampling approach adopted by the audit team. (5 marks)
(ii) Suggest alternative means of selecting the sample in which the material balances have a
greater probability of selection.(8 marks) (Total: 13 marks)

8 | Shwaibu Sella (CPA,MSc,BBA,ATEC) +255784397398

SUGGESTION SOLUTION

Question One
What the audit assistant says is not necessarily true. Whether to use sampling in an audit depends
on the professional judgment of the auditor. One factor that is essential for sampling is the existence
of a reliable internal control system.
If the small enterprise does not have good internal controls in certain areas, then sampling may not
work in those areas. However, if there are good internal controls, sampling may be used even in a
small unit.

Question Two
The following audit procedures are open to the sampling process:
(a) Tests of controls: in principle, tests of controls are open to sampling, especially when
application of control leaves audit evidence of performance. Controls on purchases of new
assets, their receipt and physical storage and recording can be checked with the help of a
sample. However, if the items are few, it may be better to verify all the items, rather than just
a sample.
(b) Tests of details
(c) Risk assessment procedures are not suitable for sampling. The auditor has to use
professional expertise to assess the risk.

Question Three

Factors influencing sample size for tests of details

Factor Effect on sample size Effect on Sample Size
An increase in the auditor’s assessment of the risk of material Increase
misstatement. For example, if the auditor assesses that the risk of
material misstatement has increased, they would increase the sample
size (or also apply other procedures).
An increase in the use of other substantive procedures directed at the Decrease
same assertion. For example, if circularization is used along with
verification of subsequent payments, the sample size may be lower.
An increase in the auditor’s desired level of assurance that tolerable Increase
misstatement is not exceeded by actual misstatement in the population.
An increase in the total error that the auditor is willing to accept Decrease
(tolerable error)
An increase in the amount of error the auditor expects to find in the Increase
population.
Stratification of the population. Decrease
For example, if the payables are stratified according to values, they
become more uniform, and therefore smaller samples are possible.

9 | Shwaibu Sella (CPA,MSc,BBA,ATEC) +255784397398

10 | Shwaibu Sella (CPA,MSc,BBA,ATEC) +255784397398
Question Four
(a) Sampling risk
Sampling risk is the risk that the auditor’s conclusion based on a sample may be different from the
conclusion if the entire population were subjected to the same audit procedure.

There are two types of sampling risks

(i) Over-optimism: the risk that the auditor will conclude
In the case of controls, that they are more effective than they actually are.
In the case of test of details, that material error does not exist when in fact it does.
(ii) Over-pessimism: the risk that the auditor will conclude
In the case of controls, that they are less effective than they actually are
In the case of test of details, that material error exists when in fact it does not

This risk affects audit efficiency, leading to additional work to establish that the initial conclusions
were incorrect.

Therefore sampling risk is controlled by the audit firm ensuring that it is using a valid method of
selecting items from a population and/or increasing the sample size.

Non-sampling risk
Non-sampling risk arises from factors that cause the auditor to reach an erroneous conclusion for
any reason not related to the size of the sample. For example, the auditor might use inappropriate
procedures, or the auditor might misinterpret evidence and fail to recognize an error.
Non-sampling risk can be mitigated by providing appropriate training for staff so they know which
audit techniques to use, and will recognize an error when one occurs, better audit planning, better
supervision and more experienced staff.

(b) The audit manager has ignored all statistical sampling techniques while suggesting that audit
tests are to be applied to all sales invoices.
This approach may be appropriate for the audit of Tam because:
 All the transactions need to be tested as the transactions although not large are material.
 The population is comparatively small, hence it would be possible to test all transactions
instead of spending time constructing a sample.

The audit senior has recommended the use of statistical sampling. This will involve a random
selection of samples using the probability theory and then applying audit tests to those invoices.
This approach may be appropriate as:
 The controls appear to function efficiently,
 There does not appear to be a change in the internal controls,
 The population is homogeneous as it is made up of similar items.

The audit junior perceives random sampling to mean a manual selection of samples. In this context

11 | Shwaibu Sella (CPA,MSc,BBA,ATEC) +255784397398

they recommend the use of ‘random’ sampling. The approach therefore involves an element of bias
and is not statistical or true ‘random’ sampling.

Although this approach saves times, it is not appropriate because:

 The selection of samples is not statistical and will have an element of bias as samples are
chosen manually and the auditor may intentionally avoid difficult items for testing.

 In case a deviation or misstatement is noticed, it may be difficult to conclude that it is an

anomaly as conclusions drawn from samples chosen using non-statistical methods may not
provide a valid conclusion.

Question Five

(b) Advantages of using statistical sampling

The main advantages gained by successfully using statistical sampling are listed below:

• It is possible to state, with a stipulated degree of confidence, that the sample result is not
further away from the true condition of the population than some specific amount.

• The result obtained by the sample is not subject to the complaint of bias, i.e. that the auditor
has looked at the worst items.

• The method provides a means of knowing in advance the size of the maximum sample
needed. If auditors have decided on the degree of risk they are prepared to accept, then
they are relieved of the obligation of determining sample sizes arbitrarily. Justification is
provided for the size of the sample used and thus for the time spent on the audit work.

• Statistical sampling can be more accurate than an examination of every time in a large
population. Examining a high volume of data involves tedious detailed work, causing
carelessness and different interpretations, and errors may arise.

• The evaluation of results is simplified, but great care is necessary, first to ensure that each
characteristic being tested is evaluated separately and, second that in fixing an acceptable
error rate". For example, a low error rate may be serious evasions of internal control but, on
the other hand, a relatively high error rate may not give concern if the errors are of a
random nature, showing no particular trend and indicating no specific control weakness.

12 | Shwaibu Sella (CPA,MSc,BBA,ATEC) +255784397398

Question Six

(a) (i) Audit efficiency may be improved as the auditor has stratified a population by dividing
it into discrete sub-populations which have an identifying characteristic. The
stratification reduces the variability of items within each stratum and therefore allows
the sample size to be reduced without a proportional increase in sampling risk
(a) (ii) Other ways by which sales population may be stratified are as under:
1. By product
2. By customers or category of customers
3. Geographically
4. Terms of sales such as credit, cash, advance etc.
Precaution: sub-categorization/sub-populations need to be carefully defined such that any
sampling unit can only belong to one stratum.

(a) (iii) Views expressed by Sohail

His view that if verification of total transaction of category A is carried out than there is no
need to perform further procedures is not correct due to the following reasons:

 The results of audit procedures applied to all the items within category A can only
provide evidence about the items that make up that category (stratum).
 The auditor should obtain sufficient appropriate audit evidence regarding items in
Categories B & C as these are also material.

Views expressed by other audit team members

Their view that proper sampling should be carried out from the total population of 640
million and categorization should be ignored altogether is not correct because stratification
helps in improving the efficiency of the audit.

(b) Circumstances in which an auditor may decide to examine entire population of items that
make up an account balance.
The auditor may decide to examine the entire population in the following circumstances:
(i) When the population constitutes a small number of large value items.
(ii) When there is a significant risk and other means do not provide sufficient
appropriate audit evidence; or
(iii) When the repetitive nature of a calculation or other process performed
automatically by an information system makes a 100% examination cost effective.

Question Seven
(a) (i) Statistical and non-statistical sampling

13 | Shwaibu Sella (CPA,MSc,BBA,ATEC) +255784397398

 An approach to sampling that has the following characteristics is called statistical sampling:
Random selection of the sample items; and
The use of probability theory to evaluate sample results, including measurement of sampling
risk.
A sampling approach that does not have above characteristics is considered non-
statistical sampling.
(ii) Sampling and Non-Sampling risk
Sampling risk is the risk that the auditor’s conclusion based on a sample may be different from
the conclusion if the entire population were subjected to the same audit procedure.
Non sampling risk is the risk that the auditor may reach an erroneous conclusion for any
reason not related to sampling risk.
(b) (i) The following shortcomings have been observed in the approach adopted by the Audit
Team:
By ignoring less than TZS. 5,000 debtors, the government debtors and some of the related
parties, for the purpose of sampling, the following important principles have not been
complied with.

That the auditor should consider the risk of material misstatement on the entire population.

That the auditor should attempt to ensure that all items in the population have a chance
of selection.
In stratification, the audit efforts are directed towards larger value items.

However, the audit planning documentation should explain why the only 10 debtors out of 50
largest debtors were selected.
(ii) Alternative means of sampling material balances are as follows:
StratificationThis would involve dividing the sample into discrete sub-populations (stratum)
which have an identifying characteristic. In our case, the population may be stratified
by monetary value. For example, following strata may be created:
Above TZS. 1,000,000
Between TZS. 500,000 and TZS. 1,000,000
Below TZS. 500,000
The sample may be made from each strata allowing effort to be directed to the larger value
items.

Value weighted selection (Monetary unit sampling)

When performing test of details, it may be efficient to identify sampling as the individual
monetary units that make up the population. In this method, each monetary unit in a
population has an equal chance of being selected for testing. Audit effort is directed to
the larger value items because they have a greater chance of selection, and can result in
smaller sample sizes.

14 | Shwaibu Sella (CPA,MSc,BBA,ATEC) +255784397398