ACT 3202 –

PRINCIPLES OF
AUDITINGLecture 7- Audit Sampling

z
 z
Audit Sampling Defined

 Audit sampling is defined as the application of a compliance or

substantive test to less than 100% of the items within an account
balance, class of transactions or other population, as
representative of that population, to enable the auditor to obtain
and evaluate evidence of some characteristic to that population
and to assist in forming a conclusion concerning that
characteristic.
 z
Stages of Audit Sampling

 Planning the sample

 Selecting the items to be tested
 Testing the items
 Evaluating the results of the test
 z Stage 1 - Planning the Sample

In planning the sample properly the factors that

the auditor considers are:
(a) The audit objectives.
(b) The population and sampling unit.
(c) The definition of error (in substantive tests) or
deviation (in compliance tests).
 z
d) The sample size, which will be
influenced by:

 The assurance required (or risk accepted) having

regard to other sources of evidence available.
 The tolerable error/deviation rate.

 The expected error/deviation rate

 The stratification.
z
 z
Objectives of Audit Sampling

 SAS 100 requires that auditors should carry out

procedures designed to obtain sufficient appropriate
audit evidence to determine with reasonable
confidence whether the financial statements are free
from material misstatement.
 z
Objectives of Audit Sampling

 Two words of relevance here are reasonable and material.

 It is not necessary that auditors should state that financial
statements are absolutely 100% accurate. Sampling does not
provide absolute proof of 100% accuracy but it can provide
reasonable assurance that some elements of the financial
statements are free from material misstatement.
 Errors can exist in the Accounts and yet the Accounts can still
give a true and fair view.
 z The following four related factors may
affect the sample size:
Assurance requires (or risk accepted)
Audit risk’ (or ‘ultimate risk’) is the risk accepted by the auditor that an
invalid conclusion will be drawn after completion of all audit
procedures.
(a) Inherent risk – the risk that material errors may occur.

(b) Control risk – the risk that the internal controls may fail to prevent
or correct such material errors.
(c) Detection risk – the risk that the auditor’s substantive tests may fail
to detect any remaining material errors.
 z

 Sampling risk, which is one component of audit risk, is the

converse of assurance required by the auditor.

The greater the degree of assurance required the larger will

be the required sample size.
 z (b) Tolerable error/deviation rate

 This is the maximum error or deviation rate the auditor is

prepared to accept in the population and still conclude that his
audit objective has been achieved.
 This is the maximum error or deviation rate the auditor is
prepared to accept in the population and still conclude that his
audit objective has been achieved.

The larger the tolerable error or deviation rate, the smaller

need be the sample size.
 z c) Expected error/deviation rate

 If the auditor expects errors or deviations to be present

before performing tests, for example, because of the results
of a previous year’s tests or his evaluation of internal
controls, he will need to take this into account in selecting an
efficient sampling method and determining the sample size.
 z (d) Stratification

 This is the process of dividing a population into sub-populations

(or ‘strata’) so that items within each sub-population are expected
to have similar characteristics in certain respects, such a
monetary value.
 z
Stage 2 – Selecting the items to be tested

 The purpose of audit sampling is to draw a conclusion about

the entire population from the sample was selected. This it is
necessary that the sample items should be selected in such a
way that they can be expected to be representative of the
population as a whole.
 z Representative selection methods
commonly used are:

 1. Random - Random sample results in a statistically unbiased sample

that may not be a representative sample

 2. Value weighted – audit of a group of contagious transactions

like delivery notes

 3. Systematic or haphazard selection- Select items on an

arbitrary basis, but without any conscious bias

 z
Stage 3 – Testing the items

 Having selected the sample items the auditor should carry out the pre-
determined audit tests for each item. If this is not possible for particular
items, alternative procedures, which provide equivalent evidence, should
be carried out on the same selected items.
 If it is not possible to carry out alternative procedures on those items the
auditor should consider the effect on his conclusions of assuming the
items to be in error.
 The auditor may eventually have to accept that the test was inconclusive
if sufficient evidence cannot be found, in which case he will seek
alternative audit evidence from other tests.
 z Stage 4 – Evaluating the results of the
tests
Having tested the items in the sample, the auditor should perform the
following steps to evaluate the results of his tests:
Analysis of errors or deviations
 In assessing any errors or deviations discovered, the auditor may
conclude that many have a common and potentially significant
feature, in which case he may decide to identify all item in the
population which possess that common feature, thereby producing
a sub-population on which he may carry out further tests.
 He should then perform separate evaluations for each sub-
population.
z
Projection of errors
 The auditor should estimate the expected error or deviation rate in the
whole population by projecting the results of the sample to the population
from which it was selected.
 This is undertaken to obtain a broad view of the scale of the possible error
or deviation rate for comparison with tolerable error and is not meant to
imply that the precise amount or rate of error in the whole population is
known.
 Accordingly projected errors should be used with great caution.
 z Assessing the risk of an incorrect conclusion

 The auditor cannot in general expect the projected error or

deviation rate to be precise measure of the actual error or
deviation rate present in the population.
 z
Summary of results
The auditor should consider, by reference to the amount which is
ultimately considered to be material to the financial statements,
the results from all audit procedures, both sampling and other, and
the total estimated unadjusted error, to determine whether he has
obtained sufficient appropriate audit evidence for each account
balance or class of transactions.
He should then aggregate these results to consider whether he
has obtained sufficient evidence for the financial statements as a
whole.
z
z
Judgemental Sampling

 This means selecting a sample of appropriate size on the

basis of the auditor’s judgement of what is desirable.
 Non-statistical sampling may use non-random sample
selection methods and does not rely on probability theory and
requires more subjectivity in making sampling decisions.
 z Advantages & Disadvantage
ADVANTAGES DISADVANTAGES
• The approach has been used for many • It is unscientific.
years. It is well understood and refined • It is wasteful – usually sample sizes are too
by experience. large.

• The auditor can bring his judgement • Personal bias in the selection of samples or
and expertise into play. Some auditors its size.
seem to have a sixth sense • There is no real logic to the selection of the
sample or its size.
• No special knowledge of statistics is • The sample selection can be slanted to the
required auditors’ needs e.g. selection of items near
the year-end to help with cut off evaluation.
• No time is spent on playing with • The conclusions reached on the evidence
mathematics. All the audit time is spent from samples is usually vague – a feeling of
on auditing. ‘it seems OK’ or of vague disquiet.
 z Statistical Sampling

 This is the drawing of inferences about a large volume of data by an

examination of a sample.
 It requires the use of random selection and uses probability theory to
determine sample size, evaluate quantitatively the sample results and
measure sampling risk.
 In practice, a high level of mathematical competence is required if valid
conclusions are to be drawn from sample evidence. However, most
firms that use statistical sampling have drawn up complex plans which
can be operated by staff without statistical training. These involve the
use of tables, graphs or computer methods.
 z Advantages & Disadvantage
ADVANTAGES DISADVANTAGES
• It is scientific. • As a technique it is not always fully
• It is defensible. understood so that false conclusions may be
drawn from the results.

• It provides precise mathematical • Time is spent playing with mathematics

statements about probabilities being which might better be spent on auditing.
correct

• It is efficient – overlarge sample sizes • Audit judgement takes second place to

are not taken. precise mathematics.
• It tends to cause uniform standards • It is inflexible.
among different audit firms.
• Lower grade staff who would be unable • Often several attributes of transactions or
to apply the judgement needed by documents are tested at the same time.
judgement sampling can use it. Statistics does not easily incorporate this.
z
Sampling Methods
The main types of statistical sampling are:
 Attribute sampling
 Variables sampling
Other sampling methods are:
 Acceptance sampling
 Discovery sampling
z Attribute Sampling
This method seeks to estimate the proportion of a population
having a particular characteristics (=attribute), for example
overdue debts or damaged stock or errors in coding invoices.
Attribute sampling has the disadvantage that it only measures
deviations from some norm but does not measure the monetary
effect of that deviation. It is generally used in compliance testing
where the extent of application of a control is to be determined.
z Variable Sampling
This method seeks to estimate (with a chosen level of
confidence and precision interval) the total value of some
population. For example the total value of debtors, stock or
loose tools. The procedure is to extrapolate from a sample to
and estimate of the total value. This estimate can be compared
with the book value and if any difference is within the materiality
limits pre-established, the auditor has evidence for the book
value of the item.
 z
Acceptance Sampling
This method seeks to discover the error rate in a population to
determine whether the population is acceptable. It involves
predetermining a maximum error rate.
It helps to determine:
1. Whether a control can be relied upon – if non-compliance is
greater than an acceptable rate, the control will not be relied
upon and other audit tests will have to be applied.
2. Whether stock calculations can be relied on. If the error rate is
greater than some acceptable proportion then the auditor will
have to request the client to do the calculations again.
z
Discovery Sampling
 This method extends acceptance sampling to an acceptance
level of nil.
 For example, a system, with controls, exists in an Investment
Trust Company to ensure that all bonus issues are accepted and
recorded. If even one bonus issue has not been recorded, the
auditor will be unable to accept the controls and will have to
seek other evidence.
 This method has been compared with seeking a needle in a
haystack. It requires large samples.
 z
Monetary Unit Sampling
This is a relatively new variant of discovery sampling which is
thought to have wide application in auditing. This is because:
a) Its application is appropriate with large variance populations.
Large variance populations are those like debtor or stocks
where the members of the population are of widely different
sizes.
b) The method is suited to populations where errors are not
expected.
c) It implicitly takes into account the auditor’s concept of
materiality.
 z Procedures for Sampling

1. Determine sample size. This will take into account:

 The size of the population

 The minimum unacceptable error rate (related to materiality)

 The Beta risk desired.

z 2. List the items in the population (we will use debtors) e.g.
 z Procedures for Sampling Cont’d

3. If the sample size were 100 items then take a random

start say 1,402 and every 3,842 item thereafter; that is using
systematic sampling with a random start
 z

 In the example, XY Co. Ltd. would be selected since 1,402 lies in their balance and
RS Acne would also be chosen as 1,402 and 3,842 lies in their balance. Note that the
larger balances have a greater chance of being selected.
 This is protective for the auditor but it has been pointed out that balances that contain
errors of understatement will have a reduced chance of detection.
 At the end of the process, evaluate the result with might be a conclusion that the
auditor is 95% confident that the debtors are not overstated by more than $x. $x is the
materiality factor chosen.
 If the conclusion is that the auditor finds that the debtors appear to be overstated by
more than $x then he may take a larger sample and/or investigate the debtors more
fully.
 z Disadvantages of Monetary Unit Sampling

 It does not cope easily with errors of understatement. A debtor balance

which is underestimated will have a smaller chance of being selected
that if it was correctly valued. Hence there is reduced chance of
selecting that balance and discovering the error.
 It can be difficult to select samples if a computer cannot be used as
manual selection will involve adding cumulatively through the
population.
 It is not possible to extend a sample if the error rate turns out to be
higher than expected. In such cases an entirely new sample must be
selected and evaluated.
z

Monetary Unit Sampling is especially useful in testing for

overstatement where significant understatements are not
expected.
Examples of applications include debtors, fixed assets and
stock. It is clearly not suitable for testing creditors where
understatement is the primary characteristic to be tested.
z Working papers
The work done in audit sampling situations should be
fully documented in the working papers. It should show:
Planning the sample
 Stating the audit objective

 Definition of error deviation

 The means of determining the sample size

 The tolerable error rate

z Working papers cont’d

Selecting the items to be tested

 The selection method used.

 Details of the items selected.

Testing the items

 The tests carried out.

 The errors or deviations noted.

z Working papers cont’d
 Evaluating the results of the tests

 Explanations of the causes of the errors or deviations. The

projection of errors or deviations.
 The auditor’s assessment of the assurance obtained as to the
possible size of actual error or deviation rate.
 The nature and details of the conclusions drawn from the sample
results.
 Details of further action taken where required (e.g. a larger sample
or other forms of evidence gathering)