AUDIT SAMPLING

by Kim Smith
01 May 1999  

This article deals with the audit methodologies of audit sampling and other selective testing
procedures from both theoretical and practical perspectives. The paper 6, Audit Framework
Teaching Guide includes:

 why sampling is inevitable;

 comparison of judgement and statistical sampling;
 attribute sampling for tests of controls;
 variables sampling for substantive procedures; and
 professional guidance.
This is assumed knowledge at paper 10, Accounting and Audit Practice, where students should
be able to “explain the use of audit sampling in the conduct of an audit”.

On the theoretical side, the professional guidance referred to is SAS 430, Auditing

Sampling (UK Stream) and ISA 530, Audit Sampling and Other Selective Testing
Procedures (International Stream).

On the practical side, audit efficiency relies on obtaining the minimum audit evidence,
sufficient to form the audit opinion, as cost effectively as possible. To this end, formalised audit
sampling procedures have been developed and become commonplace in the majority of audit
firms. The use of audit sampling, on all audit assignments, offers innumerable benefits to all
auditors. These include:

 developing a consistent approach to audit areas;

 providing a framework within which sufficient audit evidence is obtained;
 forcing clarification of audit thinking in determining how the audit objectives will be
met;
 minimising the risk of over-auditing; and
 facilitating more expeditious review of working papers.
Nature of sampling
Audit evidence is obtained by carrying out audit tests which may be classified as ‘non-
sampling’ or ‘sampling’.

A definition — Audit sampling is the testing of less than 100% of the items within a population to obtain
and evaluate evidence about some characteristic of that population, in order to form a conclusion
concerning the population.
(SAS 430 simplified)

It is crucial that the items selected should be representative, in order to be able to form a
conclusion on the entire population. For if a test is applied only to those items which have a
specific feature (e.g., all customer’s balances exceeding $20,000) this constitutes 100%
examination of a sub-population (or selective testing of high-value items) and the results cannot
 be projected to the whole population.

SAS 430 v ISA 530

Both statements of standards concern audit sampling in general i.e., both statistical and non-
statistical sampling. (It is a common misconception that these standards concern only statistical
sampling.) However, the ISA considers selective testing other than audit sampling in more
detail than the SAS.

The ISA definition of audit sampling specifically states that “all sampling units have a chance
of selection”. Thus, 100% examination and selecting specific items are clearly non-sampling
procedures.

Non-sampling tests include:

 100% examination, i.e., selecting all items in a population;

 analytical procedures;
 tests in total (also called proofs in total or logic tests) i.e., calculations of reasonableness
based on independently verified data;
 ‘walk-through’ tests, i.e., tracing a few transactions in order to obtain knowledge and
understanding of the design and operation of accounting and internal control systems; and
 other selective testing of specific items, e.g., high-value, key and unusual (but not
representative) items.
Sampling v non-sampling risk
Fundamental to audit sampling is sampling risk. This may be regarded as a component of
detection risk which determines the required level of substantive procedures (see “Audit
strategy”, G. Cosserat, Students’ Newsletter, February 1999). The other component of detection
risk is then non-sampling risk.

A definition — Sampling risk is the risk that the sample is not representative of the population from which
it is drawn and thus the auditor’s conclusion is different to that which would be reached if the whole
population was examined.
This may result in:

(a) ‘the risk of incorrect rejection’ (also called Alpha risk) which arises when the sample
indicates a higher level of errors than is actually the case. This situation is usually resolved by
additional audit work being performed. This risk affects audit efficiency but should not affect
the validity of the resulting audit conclusion;

(b)‘the risk of incorrect acceptance’ (also called Beta risk) when material error is not detected in
a population because the sample failed to select sufficient items containing errors. This risk,
which affects audit effectiveness, can be quantified using statistical sampling techniques.
Although it is possible that an unqualified auditors’ report could be issued inappropriately, such
errors should be detected by other complementary audit procedures (assuming that the sample
size is appropriate to the level of detection risk).

Non-sampling risk is the component of detection risk that is not due to examining only a portion
of the data. Examples of sources of non-sampling risk include:
 failure to investigate significant fluctuations in relationships when placing reliance on
analytical procedures; and
 placing reliance on management representations as a substitute for other audit evidence
that could reasonably be expected to be available.
Selective testing which does not constitute audit sampling (e.g., selection of risk-prone items) is
also subject to non-sampling risk. ISA 530 defines non-sampling risk as the risk which “arises
from factors that cause the auditor to reach an erroneous conclusion for any reason not related to
the size of the sample”. Thus non-sampling risk can also arise, for example, if the auditor fails
to recognise an error in an individual item in a sample. The auditor seeks to minimise the risk of
erroneous conclusions by proper planning, supervision and review.

Sampling risk is frequently expressed as a %. For example, 5% means that there is a 1 in 20

chance of material error going undetected (this is the risk accepted by many audit firms for any
specific audit tests). Risk can also be expressed in terms of confidence levels (assurance
required) and reliability factors.

A confidence level is the degree of assurance that material error does not exist; it is the converse
of risk.

Reliability (R-) factors are derived from the Poisson sampling distribution (a distribution of
‘rare events’) and are related to risk percentages as shown in Figure 1. Note the ‘inverse’ nature
of the relationship between R-factors and risk and that a confidence level is the mathematical
complement of risk.

The use of R-factors (and related methods) is popular. It makes determination of sample size
easy, avoids the need to carry statistical tables and is compatible with the Audit Risk Model as
illustrated in Figure 2. In this illustration, the risk of errors arising (inherent risk) is high, but
assurance is planned to be obtained from tests of control. The auditor’s tests of detail will
therefore be planned at a level corresponding to sampling risk of not more than 14% (seeFigure
4 later).

Deciding to sample
 When planning the audit procedures to be adopted, the decision to sample account balances and
transactions is influenced by:

 materiality and the number of items in the population;

 inherent risk (of errors arising);
 relevance and reliability of evidence available through non-sampling procedures; and
 costs and time involved.
To obtain the overall level of assurance required, a cost-effective combination of sampling and
non-sampling procedures should be determined. Audit sampling procedures are effected in four
stages: 
1 sample design; 
2 sample selection; 
3 testing (i.e., performing the audit procedure); and 
4 evaluation.

1 Sample design

Sample design, which may be set out in a sample plan, includes consideration of:

 audit objective(s) of the test;

 population from which the sample is to be drawn;
 sampling unit;
 results or conditions that will be regarded as errors or deviations;
 sample size.
Population

A definition – Population is the entire set of data from which a sample is selected and about which the
auditor wishes to draw a conclusion.
A population may be ‘stratified’, that is, divided up into sub-populations. Each sub-population
is a group of sampling units having similar characteristics. For example, current debts, debts 1–
3 months overdue, debts 3–6 months overdue and debts more than 6 months overdue.

For tests of control the population must have the same control characteristics. So, for example,
supplier’s invoices for raw materials will be distinct from supplier’s invoices for services
because the former should evidence the receipt of goods.

For substantive procedures the population could be a list of ledger balances or debit entries to
individual ledger accounts or all transactions of a particular type (e.g., weekly wages).
 Sampling unit

A definition – A sampling unit is an individual item in a population.

For example, an account balance, a debit (or credit) entry on a bank statement, a goods received
note or a monetary unit (i.e., £ or $).

Errors and deviations

In substantive procedures, an error is a misstatement. In a test of controls, an error is a control

deviation. It is vital that what constitutes an error be determined (as incorrect identification is an
example of non-sampling risk). For example, in following up a direct confirmation of accounts
receivable to confirm the amounts owed, a non-reply will not (of itself) constitute an error. If a
balance is disagreed but the reason for the difference is cash or goods-in-transit that is not an
error (providing cut-off in the books being audited is correct). If a balance is in dispute but is
settled by the issue of a credit note after the year end, that is not an error unless an allowance
(i.e., provision) has not been made for it.

Sample size

The determination of sample size requires judgement of:

 assurance required;
 tolerable and expected error (or deviation rate); and
 stratification.
Absolute assurance cannot be achieved through sampling procedures. The lower the assurance
required, the smaller the required sample size. The tolerable error (or deviation rate) is also
called precision. It is the maximum error (or deviation rate) that can be accepted to conclude
that the audit objective has been achieved. (The combined tolerable error for all audit tests is
sometimes called gauge.)

For substantive tests, precision may be expressed as a monetary amount (which is less than
overall materiality) or a percentage of population value. For tests of control, precision is the
maximum rate of failure of an internal control that can be accepted in order to place reliance on
it (and is therefore likely to be small).

Errors increase the imprecision of results from sampling. Therefore, if they are expected, a
larger sample size is required.

Stratification

Stratification, i.e., dividing up a population to create relatively homogeneous groups in which

the variation in characteristics is expected to be small, enables more time to be devoted to items
considered most vulnerable to material error. It is used mainly in substantive testing.

In conclusion to this section, a sample plan for a substantive test is set out in Figure 3. Figure
4 illustrates a sample plan for a test of controls.
2 Sample selection
 The aim of audit sampling is to form a conclusion about the population from which a sample is
obtained. It is, therefore, necessary to ensure that the method of sample selection can be
expected to produce a representative sample with each item in the population having a chance
of being selected.

The distinction between statistical and non-statistical sampling should be made clear before
considering the methods of selection.

Statistical sampling

Any approach to sampling that uses:

(i) random sample selection; and

(ii) probability theory to:

 evaluate sample results (quantitatively); and

 measure sampling risk.
The two main types of statistical sampling are Attribute sampling andVariables sampling.

Attribute sampling is concerned with testing items which can have only two possible values
(e.g., 0 or 1) or attributes (e.g., correct or incorrect). It is used to provide information about rates
of occurrence of events or characteristics. It is most widely used in tests of control (to determine
rates of non-compliance within control procedures) and Monetary Unit Sampling (see later).

Variables sampling is concerned with testing items which can take any value within a
continuous range and is therefore used in substantive tests of details.

Non-statistical sampling

Any approach to sampling which does not fulfil all the characteristics set out above for
statistical sampling. Such approaches are often referred to as judgement sampling. However, as
statistical sampling

also requires judgment, the term non-statistical is preferred.

Methods of sample selection

The standards recognise three commonly used methods of obtaining representative samples for
audit sampling:

 random number;
 systematic;
 haphazard.
Random number selection — every item in a population has the same statistical probability of
being selected as every other item. Random numbers are selected using a computer program or
random number tables.
Systematic selection — requires the calculation of a uniform sampling interval which is
obtained by dividing the population by the sample size. E.g, if 50 items are to be selected from a
population of 600 every 12th item will be selected from a randomly selected starting point
(within the sampling interval). This method is suitable for both tests of controls and substantive
tests and particularly useful for sampling from non-monetary populations as illustrated
in Figure 5.However, care must be taken to ensure that the population is not structured in such
a way that the sampling interval corresponds to a pattern in the population. For example, if cash
book payments are written up by cheques in date order with all the bank statement entries
(direct debits, bank charges, etc.,) being recorded at each month end, a sample could be biased
towards a particular transaction type.

Haphazard selection — this method attempts to give all items in a population a chance of
selection by choosing items haphazardly. To avoid conscious bias it is necessary to avoid:
favouring middle items, ignoring first and last items, selection of unusual items, etc. Sometimes
it is the only practical method (in terms of time and cost) of selecting a sample from a
population which cannot be accessed using a numerical sequence. Though sometimes used for
non-statistical sampling it is not sufficiently rigorous for statistical sampling.

Value weighted selection — this systematic selection method uses currency unit values, rather
than the items, as the sampling population. Each individual pound is given an equal chance of
selection. Since these cannot be examined, the item in which a pound selected lies is tested.
Using this method, high-value items have a greater chance of being selected. Random number
selection could be employed but usually the method involves cumulative totalling of currency
values (which can be time consuming unless computer-assisted). This is illustrated in Figure
6. The determination of Cumulative Monetary Amounts (CMA) is frequently used in Monetary
Unit Sampling (MUS). MUS is a statistical sampling technique used for substantive testing
which tests each $1 (or £1) to see if it is correct or incorrect (i.e., a form of attribute sampling).
Value weighted selection can also be used in non-statistical sampling. For example, by
stratifying the population and selecting more items from a particular strata. An example of this
is the ‘two strata’ sampling method which combines 100% selection of high-value (key) items
with the sampling of items from two strata in the remaining population. The boundary between
the two strata may be calculated as (for example) twice the average population value. The
sample selected from the two strata is then weighted towards the higher value stratum items.

Block sampling — consists of the selection ‘en bloc’ of adjacent transactions or items.

There are two major drawbacks:

(i) a block selected may not be typical of the characteristics in the population as a whole; and

(ii) relatively few blocks may be selected. It is, therefore, unlikely that a reasonable conclusion
can be drawn.

Nevertheless significant cost savings in audit time can result and practical considerations may
dictate its use. For example, when conducting an audit over numerous branches, it may be
appropriate to select just one week’s payroll or one month’s postings to the general ledger or all
customer accounts beginning with the same letter.

3 Testing the items

If the performance of a pre-determined test is not possible e.g., a document is not available,
alternative procedures to provide equivalent evidence should be adopted. If this is not possible
the effect of assuming it to be an error (or deviation) should be considered. If a test is
inconclusive alternative evidence should be sought from other tests.

4 Evaluating the results

The errors or deviations detected should be analysed and used to estimate the total error or
deviation rate in the population. The risk, that the actual error or deviation rate may exceed the
tolerable error, should be assessed.

When analysing the errors or deviations (as defined when planning the sample) their nature,
cause and possible impact on other audit areas and the financial statements as a whole should be
considered. If they have a common and potentially significant feature a sub-population of items
possessing that feature may be identified for further testing.

For substantive tests there are two quantitative methods of error projection. Their use depends
on whether or not the error relates closely (i.e., is proportional) to the size of the item.

Ratio method

This method is used if errors relate closely to the size of the items (i.e., small errors in small
balances, large errors in large balances). For example, if sales invoices for the first week of
January were all priced at December prices.

The projected error is estimated as:

Population
Error found in value
sample x
Sample
  value
This is illustrated in Figure 7. To this must be added the actual errors in items examined 100%
(if any) to give a total estimate of error. (Refinements of this method, for example, using ‘error
taintings’, ‘rankings’ and ‘precision-gap widening’ are beyond the scope of this article, the
professional guidance and the ACCA’s examination syllabuses!)
Difference method

This method is used if errors do not relate closely to the size of items but are relatively constant
for all items. A simple example would be if a credit card company charged a renewal fee of $21
per account instead of $12 per account.

Such errors can be projected by multiplying the average difference between audited (i.e.,
correct) and recorded (i.e., incorrect) amounts (i.e., $9 in the preceding example) by the total
number of items in the population. This amounts to calculating:

Number of
Error found in items in
sample x population

Number of
  items in
sample
For tests of control the number of observed deviations divided by the sample size is the best
estimate of the deviation rate in the population from which it was selected, as illustrated
in Figure 8.
Projected errors are not precise measures of the actual errors present in the population. When
using statistical sampling confidence intervals may be calculated to indicate the likely range of
possible error. Alternatively, and more commonly, judgement is used to draw a reasonable
conclusion.

Key points summary

 Not all selective testing constitutes audit sampling.

 Audit sampling is testing less than 100% of items that have a chance of selection.
 Sampling risk is the risk that a sample is not representative.
 Non-sampling risk arises from factors that cause the auditor to reach an incorrect
conclusion (for any reason unrelated to sample size).
 Four stages in audit sampling are design, selection, testing and evaluation.
 Statistical sampling requires random sample selection and use of probability theory.
 Three methods of selecting representative samples are random number, systematic and
haphazard.
 Results are evaluated qualitatively and quantitatively.
 Evaluation of sample results involves quantification and this will be examinable.

Monetary-unit-
sampling [MUS] is
less efficient and
generally not used
if:

The auditor's objective is oriented towards understatements

A)

Computerized system account balances are being audited

B)
The account contains a large book value and a large number of
C) transactions

Statistical conclusions are to be made relating to the sample

D)
Feedback:

2 INCORRECT
An auditor may decide to increase the risk of incorrect rejection when

Increased reliability based on the sample is desired.

A)

Many differences (audit value minus recorded value) are expected.

B)
The initial sample results do not support the planned level of control
C) risk.

The cost and effort of selecting additional sample items are low.
D)
 Feedback:

3 INCORRECT
When planning a sample for a substantive test of details, an auditor should
consider the tolerable misstatement for the sample. This consideration
should:

Be related to engagement risk.

A)

Not be adjusted for qualitative factors.

B)

Be related to preliminary judgments about materiality levels.

C)

Not be adjusted during the audit process.

D)
Feedback:

4 INCORRECT
In assessing sampling risk, the risk of incorrect rejection relates to the

Efficiency of the audit.

A)

Effectiveness of the audit.

B)

Selection of the sample.

C)

Audit quality controls.

D)
Feedback:

5 CORRECT
Which of the following is true with regard to the auditor's determination of
tolerable misstatement in statistical sampling of tests of balances?

It is directly related to sample size

A)

It is inversely related to preliminary levels of materiality

B)
The likelihood that an auditor will conclude that the book value of a
population being sampled is fairly stated increases as the tolerable
C) misstatement increases.

It is generally lower than expected misstatement

D)
Feedback:

6 CORRECT
An account balance is $2,250,000 and there are 55 items in the account, ten
of which have balances that equal or exceed $75,000. The auditor plans to
 use a monetary-unit sampling plan with systematic sample selection. To
ensure that all accounts with balances of at least $75,000 are selected, the
minimum sample size should be:

10.
A)

20.
B)

30.
C)

50.
D)
Feedback:

7 INCORRECT
In monetary-unit sampling, the sampling interval is

The same as sample size.

A)

Equal to the number of items in the account.

B)

Population size divided by sample size.

C)

The standard deviation of the items in the account.

D)
Feedback:

8 INCORRECT
In a probability-proportional-to-size sample with a sampling interval of
$10,000, an auditor discovered that a selected account receivable with a
recorded amount of $5,000 had an audited amount of $4,000. If this were
the only misstatement discovered by the auditor, the projected misstatement
of this sample would be

$1,000.
A)

$2,000.
B)

$5,000.
C)

$10,000.
D)
Feedback:

9
UNANSWERED Which of the following statements is true regarding audit sampling?
Audit firms are increasingly utilizing non-statistical sampling plans using
A) their own proprietary software.
 Audit firms are increasingly utilizing non-statistical sampling plans using
B) EXCEL and other commercially developed software.
Audit firms are increasingly utilizing statistical sampling plans using their
C) own proprietary software.
Audit firms are increasingly utilizing statistical sampling plans using their
D) EXCEL and other commercially developed software.

10
INCORRECT Which of the following is considered one of the main advantages of classical
variables sampling over monetary-unit sampling?
Any amount that is individually significant is automatically identified and
A) selected.
Auditors rarely need the assistance of computer software to design and
B) carry out an effective sampling plan.
Inclusion of zero and negative balances generally do not require special
C) sampling considerations.
An understanding of standard deviation and normal distribution theory is
D) not necessary.
Feedback:

11
INCORRECT An auditor is determining the sample size for an inventory observation using
mean-per-unit estimation [classical variables sampling]. To calculate the
required sample size, the auditor usually determines the Variability in the
Dollar Risk of Incorrect

Amounts of Inventory Items: Yes; Acceptance: Yes

A)

Amounts of Inventory Items: Yes; Acceptance: No

B)

Amounts of Inventory Items: No; Acceptance: Yes

C)

Amounts of Inventory Items: No; Acceptance: No

D)