CHAPTER 9 b.

Recomputing or estimating amounts

AUDIT SAMPLING FOR TESTS OF CONTROLS c. Reviewing trends in reporting
d. Comparing similar businesses
BASIC AUDIT SAMPLING CONCEPTS
 100% Examination:
NATURE AND PURPOSE a. Reviewing all fixed asset purchases,
where appropriate
In the last chapter, we learned about designing b. Examining all contracts, where there
tests of controls and substantive tests of are a smaller number
transactions needed to perform an audit. Before
these tests can be performed, the auditor needs SAMPLING AND NONSAMPLING RISK
to decide for each audit procedure the sample
The auditor, in every audit engagement, is faced
size and items to select from the population.
with uncertainty that material errors may occur
When the auditor decides to select less than
and remain undetected. This uncertainty is
100% of the population for testing for the purpose
categorized into sampling and non-sampling
of making conclusions about the population, it is
risk.
called audit sampling.
SAMPLING RISK
PAS 530, Audit Sampling and Other Testing
Procedures, provides guidance on the use of Sampling risk means the possibility that the
sampling in an audit of financial statements. auditor’s conclusion, based on a sample, may be
different from the conclusion that would have
Audit sampling, whether statistical or
been reached if the entire population were
nonstatistical, is the application of an audit
subjected to the same audit procedure.
procedure to less than 100% of the items within
an account balance or class of transactions for Exhibit 9.1 shows the sampling risk the auditor
the purpose of evaluating some characteristic of faced in both tests of control and substantive
all the items within the balance or class of procedures
transactions.
TESTS OF CONTROL SUBSTANTIVE
WHY AUDITORS SAMPLE PROCEDURES
Risk of Under Reliance Risk of Incorrect
No matter how competent the auditor or how The risk that, although the Rejection
sophisticated the software used, reviewing each sample result does not The risk that, although
account is a physical impossibility. Even if 100% support the auditor’s the sample result
of the information could be tested, the cost of assessment of control risk, supports the
the actual compliance rate conclusion that a
testing would likely exceed the expected benefits would support such an recorded account
to be derived. What is required is a sampling of assessment. balance or class of
the accounts. Also, auditor uses sampling when transactions is
the nature and materiality of the balance or class Risk of Over Reliance materially misstated, in
does not demand a 100% audit. The risk that, although, the fact it is not materially
sample result supports the misstated.
TESTING PROCEDURES WHICH DO NOT INVOLVE auditor’s assessment of
SAMPLING control risk, the actual Risk of Incorrect
compliance rate would not Acceptance
There are many audit procedures which do not support such an The risk that, although
involve sampling: assessment. the sample result
supports the
 Inquiry and Observation: conclusion that a
recorded account
a. Reviewing records for the method of balance or class of
accounting and other information transactions is not
b. Observing accounting procedures materially misstated, in
c. Discussing methods of accounting fact it is materially
and reporting with buyer misstated.
d. Scanning documents for possible
issues The risk of under reliance and the risk of
 Analytical Review Procedures: incorrect rejection audit efficiency as they would
a. Comparing records, reports, and other ordinarily lead to additional work being
information performed by the auditor, or the entity, which
would establish that the initial conclusions were ADVANTAGES DISADVANTAGES
incorrect. The risk of over reliance and the risk of a. Design an efficient Additional costs of:
incorrect acceptance affect audit effectiveness sample a. Training auditors in
and are more likely to lead to an erroneous b. Measure the sufficiency the proper use of
of evidence obtained. sampling techniques
opinion on them financial statements than c. Quantify the sampling b. Designing and
either the risk of under reliance or the risk of risk conducting the
incorrect rejection. sampling
c. Selecting items for
Sample size is affected by the level of sampling examination
risk the auditor is willing to accept from the
results of the sample. The lower the risk the
auditor is willing to accept, the greater the
TYPES OF STATISTICAL SAMPLING TECHNIQUES
sample size will need to be.
A. Attribute sampling
NON-SAMPLING RISK
B. Monetary unit sampling
Non-sampling risk is the risk of auditor error and C. Classical variable sampling
arises from:
NON-STATISTICAL SAMPLING
 Inappropriate or ineffective audit Non-statistical (judgmental) sampling is a
procedures sampling approach that relies exclusively on
 Failure to recognize error in the sample subjective judgement to determine the sample
tested size and to evaluate the sample results
 Misinterpretation of evidence obtained
TYPES OF SELECTION METHOD FOR NON-
CONTROLLING THE RISKS STATISTICAL SAMPLING
There are ways to control or minimize the A. Haphazard sampling
sampling and non-sampling risk. Auditors B. Block selection
control sampling risk by: C. Judgmental sampling
 Adjusting the sample size and Both approaches (statistical and non-statistical
 Using the appropriate method of sampling) require the use of the auditor’s
selecting sample items from the professional judgement to plan, perform, and
population evaluate the sample evidence. In other words, the
use of statistical methods does not eliminate the
Auditors minimize the non-sampling risk by:
need to exercise judgement. A properly designed
 Careful design of the audit procedures, statistical sampling. Both approaches are
and acceptable and can provide auditors with
 Proper instruction, adequate training, sufficient competent evidential matter. The
effective supervision and review of the difference between statistical and non-
audit team. statistical sampling is that statistical sampling
allows the auditor to measure quantitively the
STATISTICAL AND NON-STATISTICAL SAMPLING sampling risk associated with the procedure.
Audit sampling methods can be divided into two Figure 9.1 shows the relationship between
general approaches: statistical and non- statistical and non-statistical sampling.
statistical.
STATISTICAL SAMPLING
Statistical sampling is a sampling approach
that applies the laws of probability to aid the
auditor in designing an efficient sample, in
measuring the sufficiency of evidence obtained
and in evaluating the sample results.
Table 9.1 shows the advantages and
disadvantages of Statistical Sampling
 used by the auditor in performing the
substantive tests to determine whether an
account is materially misstated.
FACTORS AFFECTING THE SAMPLE DESIGN
In designing an audit sample, auditor should
consider the following factors:

 Audit objectives
 Population
 Risk and assurances
 Tolerable error
 Expected error in the population
 Stratification
AUDIT OBJECTIVES
Auditors first consider the specific audit
objectives to be achieved and the audit
procedures which are likely to best achieve those
objectives. In addition, when audit sampling is
appropriate, consideration of the nature of the
audit evidence sought and possible error
conditions or other characteristics relating to
that audit evidence assist auditors in defining
what constitutes an error and what population to
use for sampling. For example, when performing
tests of control over an entity’s purchasing
procedures, auditors are concerned with matters
such as whether an invoice was clerically
checked and properly approved. On the other
hand, when performing substantive procedures
on invoices processed during the period,
auditors are concerned with matters such as the
proper reflection of the monetary amounts of
ATTRIBUTE AND VARIABLES SAMPLING such invoices in the financial statements.
The auditor may use either attribute or various POPULATION
sampling when using statistical sampling.
The population is the entire set of data from
ATTRIBUTE SAMPLING which auditors wish to sample in order to reach
Attribute sampling is a statistical sampling a conclusion. Auditors would determine that the
technique used to estimate the proportion of a population from which the sample is drawn is
population that possesses a specified appropriate for the specific audit objective and
characteristic. The auditor wants to determine complete. For example, if the auditor’s objective
the deviation rate (occurrence rate) for a control was to test for overstatement of debtors, the
implemented within the entity’s accounting population could be defined as the debtors
system. Measurement of deviation rate provides listing. On the other hand, when testing for
support for the auditor’s assessed level of understatement of creditors, the population
control risk. It is normally used when performing would not be the creditors listing but rather
tests of controls. subsequent disbursements, unpaid invoices,
suppliers’ statements, unmatched receiving
VARIABLES SAMPLING reports or other populations that would provide
Variables sampling is a statistical technique audit evidence of understatement of creditors.
used to estimate the monetary value of a class of The individual items that make up the
transactions or account balance. It is normally population are known as sampling units. The