CHAPTER ONE

AUDITING SAMPLING
Objectives of the chapter:
After completing this chapter you should able to:
 Define audit sampling
 Explain rationale for and methods of Audit Sampling
 Describe Audit Sampling for test of controls
 Examine Audit Sampling for Substantive tests
1.1. Introduction to Audit Sampling
As business entities have evolved in size and complexity, auditors increasingly have had to rely
upon sampling procedures as the only practical means of obtaining for sufficient, competent
evidential matter as the basis for audit reports. This reliance upon sampling procedures is one of
the basic reasons that audit reports are regarded as expressions of opinion, rather than absolute
certificates of the fairness of financial statements.
It is neither practicable nor necessary for the auditor to check all the transactions in a client’s
accounting records or to verify or confirm all individual items comprising the assets, liabilities,
revenues, equities, and expenses. The auditor will examine only a representative sample of such
transactions and will form his/her opinion on the reliability of the accounting records as a basis
for the correctness of the financial statements under audit opinion from the results of such tests.
An audit includes examining, on a test basis, evidence supporting the amounts and disclosures in
the financial statements.” Hence, Auditors use sampling (statistical / or non statistical).

1.2. Definition of Audit Sampling.

GAAS defines audit sampling as the application of an audit procedure to less than 100 percent
of the items for the purpose of evaluating some characteristic of the balance or class.
 Sampling is the first step toward an informed opinion, not an end but a means to an end.
According to SAS # 39, Audit Sampling, three conditions must be met to constitute audit
sampling.
 Less than 100% of the population must be examined.
 Sample results must be projected as population characteristic.
 The projected sample results must be compared to an existing client-determined account
balance to determine whether to accept or reject the client’s balance, or the projected
sample results must be used to assess control risk.
For example, in determining whether inventory quantities are appropriately recorded, an
auditor may complete an internal control structure questionnaire on inventory and also may
select some items for independent count. Completing the questionnaire is a non-sampling
procedure, whereas making independent counts is a sampling procedure if the auditor
projects the sample findings to evaluate the accuracy of the client’s inventory count.

1
1.3. Rationale for Audit Sampling
 Audit sampling offers an opportunity for auditors, to obtain minimum amount of audit
evidence, which is both sufficient and appropriate, that in turns, in order to form valid
conclusions on the population.
 Audit samplings reduce risk of over auditing in certain areas and enable a much more
efficient review of working papers at review stage of the audit.

 Audit samplings intended, to obtain both sufficient and appropriate, audit evidence at
reasonable costly.
1.4. Representative Samples
In devising their sample, auditor must ensure that the sample selected must be a
representative sample of the population.
“A representative sample is one in which the characteristics in the sample are the same as
those of the population”.
This means that the sampled items are similar to the items not sampled. If a sample is not
representative of the population, the auditors will be unable to form conclusion on the
entire population.
For example if the auditor test only 20% of trade receivable for the existence of reporting date
by configuring after date of cash, this is hardly representative of the population. Whereas, says,
75% would be much more representative.
Two things can cause a sample result to be non-representative:
o Sampling risk
o Non sampling risk
a) sampling errors/Risk/:
 Is the risk that an auditor reaches an incorrect conclusion because the sample is not
representative of the population.
 Occur because of the nature of sampling; the proper sampling method was selected,
applied, and interpreted but failed to uncover material misstatements.
 It is an inherent part of sampling that result from testing less than the entire population.

Sampling risk reduced by:

o Increase sample size
o Use appropriate sample selecting method
b.) Non-Sampling Risk:
 Is a risk that the auditor forms wrong conclusions, which is unrelated to sampling risk.

2
 An example of such situation would be where the auditor adopts inappropriate audit
procedures, or does not recognize control deviation.
The two causes of non-sampling error are:
 The auditor’s failure to recognize exceptions.
This may occur because of exhaustion, boredom or lack of understanding what to look
for on the part of auditor.
 In appropriate or ineffective audit procedures.
Auditor can reduce the risk of non-sampling errors:
 Increase auditor competence through continuing professional education
 Careful design of Audit procedure and proper supervision and instruction
1.5. Approaches of Audit Sampling
An audit sampling based on statistical and non-statistical samplings approaches.

Similarities between Statistical and Non-statistical samplings:

Both approaches require:
 planning the sample,
 selecting the sample,
 performing the sample, and
 Evaluating the results and drawings conclusions.
The differences between statistical and non-statistical samplings:
Statistical sampling:
 Allows the quantification of sampling risk in planning the sample (Step 1) and evaluating
the results (Step 4).
 -Selection is a method of selecting a sample such that each population item has a known
probability of being included in the sample.
 the sampling risk can be quantified
 widely used
 assist auditors in:
(1) Designing efficient samples,
(2) Measuring the efficiency of the evidence obtained, and
(3) Objectively evaluating sample results

Non- statistical samplings:

 Are those items that the auditor believes will provide the most useful information are
selected
 Employs auditor’s professional experience and judgment

Sample Selection
In auditing, a sample should be:

3
a. Random- a random sample is one where each item of the population has an equal (or
specified) chance of being selected. Statistical inferences may not be valid unless the sample is
random.
b. Representative- the sample should be representative of the differing items in the whole
population. For example, it should contain a similar proportion of high and low value items to
the population (e.g. all the accounts receivable).
c. Protective- protective, that is, of the auditor. More intensive auditing should occur on
high value items known to be high risk.
d. Unpredictable- client should not be able to know or guess which items will be examined.
There are several methods available to an auditor for selecting items. These include:
a. Haphazard: simply choosing items subjectively but avoiding bias. Bias might come
conversely by tendency to favour items in a particular location or in an acceptable file or
conversely in picking items because they appear unusual. This method is acceptable for non-
statistical sampling but is insufficiently rigorous for statistical sampling.
b. Simple random: all items in the population have (or are given) a number. Numbers are
selected by a means which gives every number an equal chance of being selected. This is done
using random number tables or computer or calculator generated random numbers.
c. Stratified: auditors often stratify a population before computing the required sample and
selecting the sample. Stratified means dividing the population into sub population (strata= layers)
and is useful when parts of the population have higher than normal risk (e.g. high value items,
oversea customers). Frequently, high value items form a small part of the population and are
100% checked and the remainders are sampled.
d. Cluster sampling: This is useful when data is maintained in clusters (= groups or
bunches) as salary records are kept in weeks or sales invoices in months. The idea is to select a
cluster randomly and then to examine all the items in the cluster chosen. The problem with this
method is that this sample may not be representative.
e. Random systematic: This method involves making a random start and then taking every
nth item thereafter. This is a commonly used method which saves the work of computing random
numbers. However, the sample may not be representative as the population may have some serial
properties.
f. Multi stage sampling: this sampling is appropriate when data is stored in two or more
levels. For example, inventory in retail chain of shops. This stage is to randomly select a sample
of shops and the second stage is to randomly select inventory items from the chosen shops.
g. Block sampling: simply choosing at random one block of items e.g. all June invoices.
This common sampling method has none of the detailed characteristics and is not recommended.
h. Value weighted selection: this method uses the currency unit value rather than the items
as the sampling population. It is now very popular and is described more fully later in the
chapter, under unit sampling.

4
Sample Size
There are several factors which must be considered when deciding upon the sample size. These
include:
a. Population size- surprisingly, in most instances this is not important and is only relevant
in very small population.
b. Level of Confidence- Even a 100% sample (for human consideration reasons) will not
give complete assurance. Auditors work to levels of confidence which can be expressed
precisely, for example 95%.
c. Precision- from a sample, it is not possible to say that I am 95% certain that, for example,
the error rate in a population of inventory calculations is x% but only that the error rate is x% + y
% where + is the precision interval. Clearly the level of confidence and the precision interval are
related, in that for a given sample size higher confidence can be expressed in a wider precision
interval and vice versa.
d. Risk- risk is a highly important concept in modern auditing and in high risk areas a large
sample will be desirable, because high confidence levels and narrow precision intervals are
required.
e. Materiality- this is really a subset of risk.
f. Subjective Factors- this is the most important and yet difficult area of consideration.
g. Expected error/deviation rate- the theory requires that the sample size required is a
function of the error/deviation rate. This is only known after the results have been evaluated.

Statistical Sampling Audit Uses

Statistical sampling plans can be used in all auditing situations when evidence about a population
is obtained by sampling. Some popular uses include:
Compliance Testing- the issue of sales credit notes is controlled by the requirements that all
such should be approved by a departmental manager and this approval evidenced by a signature.
The auditor would wish to confirm that this control was compiled with by sampling the sales
credit notes.
Substantive Testing- in a client with very unreliable internal controls, the auditor may wish
to verify that all dispatches in year have resulted in invoices in that year. The correspondence
between dispatch note and invoice can be sampled.