AUD 589

AUDITING 1

Audit Sampling

Prepared by:
Yusarina Mat Isa
UiTM Kampus Puncak Alam
 Learning Objectives
 Able to:
Explain audit sampling and the types and
classification of sampling

2
 Audit Sampling

AUDIT EVIDENCE (ISA 500)

• The auditor should obtain sufficient appropriate audit
evidence to be able to draw reasonable conclusions
on which to base the audit opinion.
• In forming the audit opinion, the auditor does not
examine all the information available because
conclusions ordinarily can be reached by using
sampling approaches and other means of selecting
items for testing.

3
 Audit Sampling

DEFINITION

ISA 530: Sampling involves the application of audit procedures to less

than 100% of items within an account balances or class of transaction
such that all sampling units have an equal chance of selection. This
enable the auditor to obtain and evaluate audit evidence about some
characteristic of the items selected in order to form or assist in forming a
conclusion concerning the population from which the sample is drawn

Express opinion in Auditors Report: An Audit

includes examining, on a test basis, refers to
the audit work carried on sampling basis

Audit sampling can use either a

statistical or a non-statistical approach

4
 Audit Sampling
Audit sampling among firms

Vary between each audit firms practices.

Common approach is random sampling.

Other types of testing:

• High valued items. 100% test on individual items selected
because they are high value or suspected to be error such
as overdue account receivables. Other items, if immaterial
testing based on sampling.
• Other items. Based sampling on a certain amount . E.g.
testing 80% on all balance sheet items.
5
 Sampling Risk
• Sampling risk (DEFINITION) is that the
auditor’s conclusion based on the sample
may be different from conclusion that would
be reached if a 100% examination were
carried out.
• Example: Auditor testing on control
procedures for payment cycle. Suppose
Auditors know client has 1000 payment
voucher during the year and 50 of those
SAMPLING payment vouchers are not properly approved
RISK (5%). Therefore, if 20 representative sample
selected, should contain 19 sample correctly
approved and 1 not properly approved (5%).
BUT sometimes from 20 samples maybe
contained 5 samples were not properly
approved (25%, considered material) OR may
be all the samples are properly approved
(Considered immaterial at all).
• Auditor can lower the sampling risk by
increasing the sampling size.
6
 Sampling Risk
Two types of sampling risk

In the compliance test or test

In the substantive test
on control

Type 1: Risk of assessing control Type 1: Risk that the auditor will
risk too high – is the risk that conclude that there is a material
the auditor will conclude that error when, in fact, it does not
the risk is higher than it is exist
actually is

Type 2: Risk of assessing control Type 2: Risk that the auditor will
risk too low – is the risk that conclude that a material error
the auditor will conclude that does not exist, in fact, it does exist
the risk lower than it is actually
is
7
 Non-sampling Risk

NON SAMPLING RISK

Non-sampling risk refers to factors that cause auditors to reach a

conclusion other than the sampling size. Example: Auditor rely on
another representation on erroneous information

Other examples: Misinterpretation of evidence, human mistakes such

as failing to recognize errors in documents and applying auditing
procedures that are inappropriate to the audit objectives

*Non-sampling risk can never be a mathematical measured.

However, to keep this risk to minimum level, proper planning and
supervision and adhere to the quality control standards is essential.
8
 Types of Sampling

TYPES OF AUDIT
SAMPLING

NON STATISTICAL
STATISTICAL SAMPLING SAMPLING
(PROBABILISTIC
SAMPLING) (NON PROBABILISTIC OR
JUDGMENTAL SAMPLING)

9
 STATISTICAL SAMPLING (PROBABILISTIC SAMPLING)
Statistical sampling means any approach to sampling that
has the following characteristics:

Use of probability
theory to
Random
evaluate sample
selection of a
results, including
sample
measurement of
sampling risk

Statistical sampling
permit the auditor to
Defend measure at
rely on a smaller
the court as it is
sample for an
systematic approach
intensive checking and
of selecting sample
make representative
to a large population

10
 NON STATISTICAL SAMPLING
(NON PROBABILISTIC OR JUDGMENTAL SAMPLING)

When auditor uses his The auditor must rely

A sampling approach
professional judgment on his professional
that does not have
to select the sample judgment rather than
above characteristic is
and evaluate sample the laws of probability
considered non-
when conducting audit to reach a conclusion
statistical sampling
test about the audit test

Auditor may use non-

Auditor will select those
random selection methods
samples item that he
& requires more
believes able to provide
subjectivity in making
useful information
sampling decisions

11
 Statistical Sampling

Monetary
Unit
Sampling
Classical
Attribute
Variable
Sampling
Sampling

CATEGORIESO
F STATISTICAL
SAMPLING

12
 Statistical Sampling

Attribute Sampling
• Used to estimate the proportion of a population that posses a specified
characteristics (Example: looking for deviation rate). The most common use
is for test of control such as auditor wants to determine the deviation rate
for control implemented in accounting system or internal control structure.

• E.g. Examination on how often a credit check is not performed (deviation

from normal procedures, i.e. before approval sales credit, we should check
the credit availability of a certain customer) on customer orders before
deliver the good or before approve another credit sales.

13
 Statistical Sampling
Monetary Unit Sampling
• It uses attribute sampling theory and techniques to estimate the amount of
misstatement for a class of transactions or an account balance.

• Designed primarily to test for overstatement errors and most appropriate

for low error rate population of the sample results.

• It express a conclusion in monetary amounts rather than as a rate of

occurrence:
• E.g. auditing accounts receivable, loans, investment securities and
inventory
• E.g. Assume that auditor has established a materiality level of
RM100,000, any misstatement more than that considered material

14
 Statistical Sampling
Classical Variable Sampling
• It uses normal distribution theory to evaluate the characteristics of a
population based on sample data of which data should have equal chance
of selection.
• Determine the range of the data and selecting sample base on random
table or computer audit software currently practiced by most big
accounting firm for their big clients.
• The purpose:
• To estimate the amount for a class of transactions or account balance
• To determine if a class of transactions or account balance is materially
misstated
• E.g. auditing account receivable in which a large amount of misstatement is
expected, and inventory in which significant audit differences are expected
for test counts and pricing tests.

15
 Statistical Sampling

When to use statistical sampling

The decision whether to use a statistical or non-statistical sampling

approach is a matter for the auditor’s judgment regarding the most
efficient manner to obtain sufficient appropriate audit evidence in
the particular circumstances

Example situations where statistical sampling can be used:

• The client’s accounting and internal control system are
reliable and effective
• The population are very large
• All items in the population are homogeneous
• All items in the population are identifiable and accessible

16
 Statistical Sampling
ADVANTAGES: It helps the auditor to:-
• Design an efficient sample
• Measure the sufficiency of evidence obtained
• Quantify sampling risk because sample is select based on statistical theory
• Permit the auditor to rely on a smaller sample
• Permit the auditor a more intensive examination of sample items since with
smaller sample sizes
• Plan the audit approach in systematic and scientific manner
• Defend measure at the court as it is systematic approach of selecting sample

DISADVANTAGES include additional costs of:

• Training auditors in the proper use of sampling techniques (statistic)
• Designing and conducting the sampling application (Software)

17
 Non-statistical Sampling

As discussed above, sampling approach that does not have

above characteristic is considered non-statistical sampling

Why auditors used non-statistical sampling:-

• Part of the reasons is due to the auditor needs to consider the
relationship between the cost of obtaining audit evidence and the
usefulness of the information obtained
• Often less costly and less time consuming but can be just as
effective in satisfying audit objectives

18
 Non-statistical Sampling
ADVANTAGES OF NON STATISTICAL SAMPLING

The ease of
The lower training Proposed adjustment
implementation of
cost of non-statistical based on quantitative
non-statistical
sampling analysis
sampling

DISADVANTAGES OF NON STATISTICAL SAMPLING

Training The absence of Potential May cause incorrect

difficulties – no consistency litigation evaluation of
systematic ways and uniformity problems sampling risk

19
 Similarities- SA vs. NSA
SELECTING THE
SAMPLE: Involves
PERFORMING
choosing sample
THE AUDIT
items such that
PROCEDURE:
all sampling units
Should meet the
in the population
audit objectives
have a chance of
selection
EVALUATING THE
DESIGN OF THE SAMPLE
SAMPLE: Audit RESULTS:
SIMILARITIES Involves error
tests are BETWEEN STATISTICAL
performed to the analysis,
AND NON STATISTICAL projection of
desired sampling SAMPLING
risk and to error and
(in terms of steps of drawing final
minimize non-
audit sampling conclusion on
sampling error
application) the sample
results20
 Differences- SA vs. NSA
STATISTICAL SAMPLING NON STATISTICAL SAMPLING
Need to have knowledge on Base on experience and common
statistical formula sense

Objective results – samples are Subjective results – the sample

mathematically proven to may not represent the population
represent population

Different auditor with the same Different auditor will have

approach will give same answer different approach and as a result
will give different answer

It is an efficient method and can It is not an efficient method and

delegate the responsibility to need more senior audit staff to
select audit sample to lower rank devise the sample and select the
audit staff sample
Defensible in the court of law Not defensible in the court of law

21
Application of Sampling on Audit Tests
Regardless of whether statistical or non statistical, the common
steps of application of sampling on audit tests are:

1)
2)
Planning the sample/Design
Selecting the sample
the sample size (e.g. more
(Basis of selection, e.g.
than RM10,000 or invoice
every five)
no from 1500 to 2000)

4)
3)
Evaluating the results
Testing the sample
(Percentage of population
(Vouching)
and conclusion)

22
Application of Sampling on Audit Tests

1) PLANNING THE SAMPLE

• When designing an audit sample, the auditor should consider
the objectives of the audit procedure and the attributes of the
population from which the sample will be drawn.
• This is important to ensure that all, and only, those conditions
that are relevant to the objectives of the audit procedure are
included in the projection of errors.
• “Population” means the entire set of data from which a sample
is selected and about which the auditor wishes to draw
conclusions.

23
Application of Sampling on Audit Tests
1) PLANNING THE SAMPLE
- Involves the following steps:

ii) Defining iii) Identifying

i) Determining
what errors or the population
the objective of
deviations are and sampling
the test
being sought unit

v) Deciding the iv) Stratification

sample size of population

24
Application of Sampling on Audit Tests
1) PLANNING THE SAMPLE
- Involves the following steps:
i) Determining the objective of the test
• The auditor to consider specific objective to be achieved and the
audit procedures to be performed towards this objective.
Example the objective is to evaluate the effectiveness of
internal control on payment procedures.

ii) Defining what errors or deviations are being sought

• Auditor to consider the factors that constitute the error by
referring the objective of the test. Example, in evaluate the
effectiveness of internal control on payment procedures, factor
constitute the error such as document not properly approved,
not properly support with proper documents or not proper
posting to respective ledger.
25
Application of Sampling on Audit Tests
1) PLANNING THE SAMPLE
- Involves the following steps:

iii) Identifying the population and sampling unit

• Audit must be very careful to identify the population and sampling unit.
Decide whether the population need to sub diving into subpopulation or
not, known as stratified the sampling. The objective is to focus greater
audit work on areas that are of high inherent risk or potentially materially
misstated. Monetary value is the most common method of stratifying a
population, particularly asset balances.

iv) Stratification of population

• “…. The process of dividing a population into subpopulations, each of
which is a group of sampling units which have similar characteristics.” For
example: Trade receivable has 40 items. The items are then divided into
the following range:
• More than RM10,000 = 3 items
• Between RM5,000 – RM10,000 = 10 items
• Less than RM5,000 = 27 items, TOTAL 40 items.
26
Application of Sampling on Audit Tests
1) PLANNING THE SAMPLE
- Involves the following steps:

v) Deciding the sample size

• The auditor main concern is to reduce sampling risk to an
acceptable low level.
• The larger the sample selected – the more representative
of the population it is likely to be.
• The main purpose to choose sampling are to save time
and cost.
• Example from the above Stratification of population.
Auditor decide sample size of 15. They may chose ALL (3)
items more than RM10,000, six for RM5k to RM10k and
six for the item below RM5k.

27
Application of Sampling on Audit Tests
1) PLANNING THE SAMPLE
- Involves the following steps:

v) Deciding the sample size (Continue…)

• Factors that influence sample size for test of control:
• Auditor’s intended reliance on internal control
• Tolerable rate of error
• Expected rate of error in the population
• The required confident level
• Factors that influence sample size for substantive procedures:
• Assessment of inherent risk
• Assessment of control risk
• Use of other substantive procedures, e.g. confirmation etc
• The required confident level
• Tolerable error
• Expected rate of error in the population
28
 Application of Sampling on Audit Tests

2) SELECTING THE SAMPLE

• The sample that should be selected is the sample that can be expected to
represent the population. All items should have equal chance of selection.
• Statistical sampling requires that sample items are selected at random so
that each sampling unit has a known chance of being selected. The sampling
units might be physical items (such as invoices) or monetary units.
• With non-statistical sampling, an auditor uses professional judgment to
select the items for a sample. Because the purpose of sampling is to draw
conclusions about the entire population, the auditor endeavors to select a
representative sample by choosing sample items which have characteristics
typical of the population, and the sample needs to be selected so that bias is
avoided.
• The principal methods of selecting samples are the use of random number
tables or CAATs, systematic selection and haphazard selection.
29
Application of Sampling on Audit Tests
2) SELECTING THE SAMPLE
- Principal methods of selecting samples:

RANDOM SAMPLING

• Generally considered as the best method of obtaining a sample. Each

item in the population has an equal chance of selection. A
computer/numbers tables may be used to generate random
numbers to tests (e.g. for documents or customer accounts).
• The advantage – does not allow auditor bias to affect the selections
of the sample due to all sample have a chance of being selected.

30
 Application of Sampling on Audit Tests
2) SELECTING THE SAMPLE
- Principal methods of selecting samples:

SYSTEMATIC SELECTION
• The auditors have determine a sampling interval by dividing the physical
population by the sample size. A starting number is selected in the first
internal and then every n th item is selected.
• For example sample size is 15, and having determined a starting point within
the first 3, each 3th sampling unit thereafter is selected. Although the
starting point may be determined haphazardly, the sample is more likely to
be truly random if it is determined by use of a computerized random number
generator or random number tables.

31
 Application of Sampling on Audit Tests
2) SELECTING THE SAMPLE
- Principal methods of selecting samples:

HAPHAZARD SAMPLE
• Selection of a sample without a specific reason (without bias) or structured
technique. Auditor must take care to avoid bias.
• Sometimes this is the only practical method when the population is not
ordered in any numerical sequence order.
• Useful for non-statistical sampling but not really recommended if other
method is available because of the auditor tend to bias.
• This method is inappropriate when the auditor using statistical sampling
because the auditor cannot measure the probability of an item being
selected.

32
Application of Sampling on Audit Tests

3) TESTING THE SAMPLE/PERFORM THE AUDIT PROCEDURES

• The auditor should perform audit procedures appropriate to the
particular audit objective on each item selected.

• Sample selected not appropriate due to void. If a selected item is not

appropriate (not because of error, but may be because of transaction
void), the audit procedure should be performed on a replacement item.

• For example, a voided check may be selected when testing for evidence
of payment authorization. If the auditor is satisfied that the check had
been properly voided such that it does not constitute an error, another
sample need to choose.

33
 Application of Sampling on Audit Tests
3) TESTING THE SAMPLE/PERFORM THE AUDIT PROCEDURES
• Sometimes however, the auditor is unable to apply the designed audit
procedures to a selected item because, for instance, documentation
relating to that item has been lost.
• Before the auditor decide that it is an error and may cause
misstatement, auditor should perform an alternative test. Example: If
an invoice missing for a debtor, auditor may do another test such as to
check the subsequent received by looking at bank statement, debtor
ledger and official receipt which normally attached with debtor’s
payment voucher and also agreed the balance with the confirmation
received from respective debtors.
• The missing invoice normally reported in the management letter from
the auditor to client on internal control system.

34
 Application of Sampling on Audit Tests

4) EVALUATING THE RESULTS

• Each error discovered will need to be examined for its implication. An
error that consistent with expectations during the planning stage can be
projected to have an impact on the population.

• Analyse nature and cause of error. Before drawing final conclusions

about the population (example: trade receivable is fairly stated) the
auditor should consider the qualitative aspect of error. Example, error
and effect to the disclosure requirement or whether intentional error
(fraud).

35
 Application of Sampling on Audit Tests

4) EVALUATING THE RESULTS

• Projecting the error. Auditor projects the sample result to the
population tested and compares these results with the minimum error
he willing to accept.
• Example for test of control if the projected error is exceed the
tolerable error rate, the auditor would conclude that the control
procedure is not operating effectively and the preliminary
assessment of control risk should be revised.

• Example for substantive test, if the projected error is higher than the
tolerable error, then the auditor would conclude that the account
balance is materiality misstated.

36
 Application of Sampling on Audit Tests
4) EVALUATING THE RESULTS
• Draw final conclusion. Auditor should evaluate the sample result to
determine whether assessment of population is confirmed or needs to
be revised. Find out the substantial error or misstatement found.
• When the results indicate error due to ineffective internal control or
balance materially misstated, auditor should:-
• Request management to investigate identified errors and the
potential for further errors, and to make any necessary adjustments;
and/or
• Modify the nature, timing and extent of further audit procedures. For
example, in the case of tests of controls, the auditor might extend the
sample size, test an alternative control or modify related substantive
procedures until further confirm; and/or
• Consider the effect on the audit report.

37
End of Topic 3c