Chapter 17

Basic Audit
Sampling
Concepts
Nature and Purpose of Audit Sampling
SAMPLING is a process whereby information is gained concerning the characteristics
of population (universe or field) of items by means of an examination of only a portion
of the items composing that population. Sampling is therefore considered an
inferential technique and it allows an auditor to draw conclusions about transactions
or account balances without sustaining the time and cost of examining all
available data.

PSA 530 (Redrafted), “Audit Sampling” establishes standards provides guidance

when the auditor has decided to use audit sampling in performing audit procedures. It
deals with the auditor’s use of statistical and non-statistical sampling when designing
and selecting the audit sample, performing tests of controls and tests of details, and
evaluating the results from the sample.

PSA 530 (Redrafted), defines audit sampling as the application of a compliance or

substantive procedures to less than 100% of the items within an account balance or
class of transactions to enable the auditor to obtain an evaluate evidence of some
characteristics of the balance or class and to form or assist in forming a conclusion
concerning that characteristic.
 Why Auditors Sample
Auditors use audit sampling when

(a) the nature and materiality of the balance or class does not demand a
100% audit

(b) a decision must be made about the balance or class; and

(c ) the time and cost to audit 100% of the population would be too great
 Testing Procedures Which Do Not Involve Sampling
It is important to recognize that certain testing procedures do not come within the definition
of sampling. Examples of these audit procedures are:

1. Tests performed on 100% of the items within a population. For example, some audit plans
include the audit of all “large” accounts and a portion of the small accounts. In such situations only the
“small” accounts would be subject to sampling. Applying audit procedures to all items within a population
which have a particular characteristic does not qualify as audit sampling with respect to the portion of the
population examined nor with regard to the population as a whole, since the items were not selected
from the total population in a basis that was expected to be representative. Such items might imply some
characteristics of the remaining portion of the population but would be necessarily be the basis for a valid
conclusion about the remaining portion of the population.

2. Inquiry and observation

a) Procedures that depend on segregation of duties or that otherwise provide no documentary evidence.
b) Tracing one or a few transactions to obtain an understanding of an accounting system and its internal
control. Procedures performed to obtain an “understanding of the internal control structure sufficient
to plan an audit” do not involve sampling. However, many “tests of controls” used to assess control
risk do involve sampling.

3. Analytical procedures
These involve the analysis of significant ratios and trends including the resulting investigation of
fluctuations and relationship that are inconsistent with other relevant information or deviate from
predicted amounts.
 Sampling vs. Non-sampling Risk
In every audit engagement a degree of risk is always present even when all transactions and
balances are tested 100 percent. This uncertainty is referred to as ultimate risk and is a
combination of sampling and non-sampling risks.

SAMPLING RISK
This refers to the risk that the auditor’s conclusion based on a sample might be different from the conclusion
they would reach if they examined every item in the entire population. This is also the probability that a
material error will occur during the accounting process. The two types of sampling risk are:

(a) The risk the auditor will conclude, in the case of a test of control, that control risk is lower than it
actually is, or in the case of a substantive test, that a material error does not exist when in fact it
does. This type of risk affects audit effectiveness and is more likely to lead to an inappropriate
audit opinion; and
(b) The risk the auditor will conclude, in the case of a test of control, that control risk is higher than
it actually is, or in the case of a substantive test, that a material error exists when in fact it does
not. This type of risk affects audit efficiency as it would usually lead to additional work to
establish that initial conclusions were incorrect.

NON-SAMPLING RISK
This refers to the probability that a material error will not be discovered by the auditor in the performance
of the substantive tests. Non-sampling risk arises from factors that cause the auditor to reach an erroneous
conclusion for any reason not related to the size of the sample.
 Nonstatistical and Statistical Sampling

Nonstatistical or Judgment sampling procedures are designed and executed on the basis
of the auditor’s sound objective reasoning judgment.

Although judgment sampling can involve arithmetic concepts, subjective influence and
probabilities reasoning, they are not formally derived from mathematical sampling proofs
and theorems. Findings from judgment sampling must always be interpreted subjectively
in the professional judgment of the auditor.

Statistical sampling is a mathematically derived tool which provides the auditor with an
objective basis for expressing conclusions about population characteristic based upon a
sample of items from the population. Statistical sampling means any approach to sampling
that has the following characteristics:
(a) Random selection of a sample; and
(b) Use of probability theory to evaluate sample results, including measurement of
sampling risk.
 Common variations of nonstatistical sampling:
Haphazard Sampling
-consists of sampling units without any conscious bias that is without any special reason for
including or omitting items from the sample. For example, a haphazard sample of vouchers
contained in a file drawer might be selected by pulling vouchers from the drawer without
regard for the vouchers’ size, shape or location of the drawer.

Block Selection
-consists of all items in a selected time period, numerical sequence, or alphabetical
sequence. For example, the auditor might examine all cash disbursement transaction in
the first week of June or the last week of December. Due to the relatively large number of
blocks needed to form a reasonable audit conclusion, block sampling cannot generally be
relied upon to efficiently produce a representative sample and therefore is not acceptable
for statistical or nonstatistical audit sampling.

Judgmental Sampling
-under this method, the auditor selects large or unusual items from the population and uses
some other judgmental criterion for selection. Obviously, this selection method has a
conscious bias and cannot be considered a representative selection method.
 Statistical Sampling (continued…)
Selecting Items for Testing to Gather Audit Evidence
When designing audit procedures, the auditor should determine appropriate means of
selecting items for testing. The means available to the auditor are:

(a) Selecting all items (100% examination);

(b) Selecting specific items, and

(c) Audit sampling

Whether auditors use statistical sampling or nonstatistical sampling methods, auditors must
decide on:

(1) Selecting all items (100% examination),

(2) Selecting specific items,

(3) Which sampling techniques to use

 Relationship between Nonstatistical and Statistical Sampling
Determine Objective of Test

Determine Procedures to Meet Objectives

How Many Items

to be Examined?
Statistical Nonstatistical

Type of Sampling

Determine Sample Size Judgmentally Determine Sample

From Model Explicitly Size Implicitly Recognizing
Recognizing Relevant Factors Relevant Factors

Judgmentally Select
Randomly Select
Representative Sample
Representative Sample

Apply Audit Procedures

Apply Audit Procedures

Evaluate Results
Evaluate Test Results
Judgmentally
Statistically and Judgmentally
Document Conclusions
Determine Effect on
Substantive Test
 Attribute and Variables Sampling Techniques
The auditor may use sampling procedures to measure both qualitative and quantitative
characteristics of a population.

Attribute Sampling Technique

Attribute estimation procedures measure qualitative characteristics, while variables estimation procedures
measure qualitative characteristics.

The auditor uses attribute estimation sampling when he or she is interested in measuring a qualitative
feature, such as presence or absence of internal control procedure. When conducting tests of controls,
The auditor must consider both the risk of overreliance and the risk of underreliance.

The risk of overreliance is the risk that the sample supports reliance on internal control when this reliance is
unjustified.

The risk of underreliance is the risk that the sample does not support reliance on internal control when the true
compliance rate suggests that the auditor should rely on internal control. If this happens, the result will be
decreased efficiency in the form of increased substantive testing procedures.

The auditor can determine the upper precision limit by considering the (1) sample size, (2) reliability, and
(3) number of observed deviations. The upper precision limit is a rate of occurrence which statistically
exceeds the actual population error rate. The auditor then compares the upper precision limit to
tolerable error to determine whether he or she can rely on internal controls related to the attributes
examined. If the upper precision limit is less than the tolerable error, the sample results suggest that the
auditor should rely on the internal control(s) examined.
 Attribute and Variables Sampling Techniques
(continued…)

Variables estimation sampling is used by the auditor during substantive testing.

this provides an estimate of a peso range within which the true audited value of
the population lies. For example, the auditor uses variables estimation sampling
to determine whether the book value of an account balance is fairly stated.

As in sampling for attributes, variables estimation sampling exposes the auditor to two aspects
of sampling risk: (1) the risk of incorrect rejection and (2) the risk of incorrect acceptance.

The risk of incorrect rejection or alpha (α) risk is the risk that the sample supports the conclusion that
the recorded account balance is materially misstated when I is not materially misstated.

The risk of incorrect acceptance or beta (β) risk is the risk that the sample supports the conclusion
that the recorded account balance is not materially misstated. This is also referred to as detection risk.
 Design of the Sample
Factors that the auditor should consider in designing an audit sample

Audit objectives

Population and its characteristics

Risk and assurance

Tolerable error

Expected error in the population, and

Stratification
 AUDIT OBJECTIVES
When designing an audit sample, the auditor should consider the objectives of the test and
the attributes of the population which the sample will be drawn.
The auditor first considers the specific objectives to be achieved and the combination of
audit procedures which is likely to best achieve those objectives. Consideration of the
nature of the audit evidence sought and possible error conditions or other characteristics
relating to that audit evidence will assist the auditor in defining what constitutes an error
and what population to use for sampling.

POPULATION
It is important for the auditor to ensure that the population is:

(a) Appropriate to the objective of the sampling procedure.

(b) Complete
 RISK AND ASSURANCE
The auditor considers what conditions constitute an error by reference to the objectives of the
test. A clear understanding of what constitutes an error is important to ensure that all, and only,
those conditions that are relevant to the test objectives are included in the projection of errors.

For example, in a substantive procedure relating to the existence of accounts receivable, such as
confirmation, payments made by the customer before the confirmation date but received shortly after that
date by the client are not considered an error. Also, a misposting between customer accounts does not
affect the total accounts receivable balance.

In planning the audit, the auditor uses professional judgment to assess the level of audit risk
that is appropriate. This audit risk includes

the risk that material errors will occur (inherent risk)

the risk that the client’s system of internal control will nor prevent or correct such
errors (control risk), and

the risk that any remaining material errors will not be detected by the auditor
(detection risk)
 TOLERABLE ERROR
This is the maximum error in the population that the auditor would be willing to accept and
still conclude that the result from the sample has achieved his audit objective. There is an
inverse relationship between the tolerable error and the required sample size. The
smaller the tolerable error, the larger sample size the auditor will require.

EXPECTED ERROR IN THE POPULATION

When performing tests of control, the auditor generally makes a preliminary assessment of the rate of
error the auditor expects to find in the population to be tested and the level of control risk. This
assessment is based on the auditor’s prior knowledge or the examination of a small number of items
from the population.

FACTORS TO BE CONSIDERED IN DETERMINING THE EXPECTED ERROR IN POPULATION

a) error levels identified in previous audits,

b) changes in client procedures, and

c) evidence available from his evaluation of the system of internal control and
from results of analytical review procedures
 STRATIFICATION
Stratification is the process of dividing a population into subpopulation, that is, a group of
sampling units which have similar characteristics (often monetary value). The reduction in
variability within each stratum results in a smaller overall sample size. Then one of the
random selection methods is used to select sample items from each stratum. Stratification
enables the auditor to direct his efforts towards the items he considers would potentially
contain the greater monetary error.

For example, 20% of the items in a population may make up 90% of the value of an
account balance. The auditor may decide to examine a sample of these items. The auditor
evaluates the results of this sample and reaches a conclusion on the 90% of value
separately from the remaining 10% (on which a further sample or other means of
gathering evidence will be used, or which may be considered immaterial).

Value Weighted Selection

It will often be efficient in substantive testing, particularly when testing for overstatements,
to identify the sampling unit as the individual monetary units (e.g., pesos) that make up an
account balance or class of transactions. Having selected specific monetary units within
the population, for example, the accounts receivable balance, the auditor then examines the
particular items, for example, individual balances, that contain those monetary units. This
approach to defining the sampling unit ensures that audit effort is directed to the larger
value items because they have a greater chance of selection, and can result in smaller
sample sizes.
 Selecting the Sample
The auditor should select items for the sample with the
expectation that all sampling units in the population have
a 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.
 Sample Selection Methods
Random Sampling
A simple random sample is a sample that is selected in such a way that every item in a population has
an equal chance of being selected. This is accomplished by using a printed table of random numbers
or computer software that generates random numbers.

Systematic Sampling
In using this method, the auditor counts through the population and selects items on the basis of a
sampling interval which is determined by dividing the number of physical items in the population by
sample size. The interval may also be based on certain number of items (e.g. every 25 th voucher
number) or on monetary totals (e.g. every P1,500 in the cumulative value of the population).

Stratified Random Sampling

As previously explained, when a population is highly variable, sampling without stratification requires
very large sample size. To stratify, the auditor groups the population into subpopulation, or strata that
are similar in amount. Samples are then drawn from each stratum using one of the random selection
methods.

Sampling with Probability Proportional to Size

This method of sampling emphasizes larger peso items within an account balance. The probability of an
item being selected in this method is directly proportional to its peso amount. For example, a P10,000
item has twice the chance being selected as a P5,000 item and ten times the chance of a P1,000
item. Each individual peso in the account balance has an equal chance of selection, but each
physical unit does not.
 Sample Size
In determining the sample size, the auditor should consider
whether sampling risk is reduced to an acceptably low level.
Sample size is affected by the level of sampling risk that the
auditor is willing to accept. The lower the risk the auditor is
willing to accept, the greater the sample size will need to be.

The sample size can be determined by the application of a

statistically-based formula or through the exercise of
professional judgment objectively applied to the
circumstances. Appendices 2 and 3 of PSA 530 (Redrafted)
indicate the influences that various factors typically have on
the determination of sample size, and hence the level of
sampling risk.
 Examples of Factors Influencing Sample Size for Tests of Control
EFFECT ON
FACTOR SAMPLE SIZE
1. An increase in the extent to Increase The more assurance the auditor intends
which the auditor’s risk to obtain from the operating
assessment takes into account effectiveness of controls, the lower the
relevant controls auditor’s assessment of the risk of
material misstatement will be, and the
larger the sample size will need to be.
When the auditor’s assessment of the
risk of material misstatement at the
assertion level includes an expectation
of the operating effectiveness of
controls, the auditor is required to
perform tests of controls. Other things
being equal, the greater the reliance the
auditor places on the operating
effectiveness of controls in the risk
assessment, the greater is the extent of
the auditor’s tests of controls (and
therefore, the sample size is increased).

2. An increase in the tolerable Decrease The lower the tolerable rate of

rate of deviation deviation, the larger the sample size
needs to be.
Examples of Factors Influencing Sample Size for Tests of Control
(continued…)

EFFECT ON
FACTOR SAMPLE SIZE
3. An increase in the expected Increase The higher the expected rate of
rate of deviation of the deviation, the larger the sample size
population to be tested needs to be so that the auditor is in a
position to make a reasonable estimate
of the actual rate of deviation. Factors
relevant to the auditor’s consideration
of the expected rate o deviation include
the auditor’s understanding of the
business (in particular, risk assessment
procedures undertaken to obtain an
understanding of internal control),
changes in personnel or in internal
control, the results of audit procedures
applied in prior periods and the results
of other audit procedures. High
expected control deviation rates
ordinarily warrant little, if any, reduction
of the assessed risk of material
misstatement.
 Examples of Factors Influencing Sample Size for Tests of Control
(continued…)

EFFECT ON
FACTOR SAMPLE SIZE
4. An increase in the auditor’s Increase The greater the level of assurance that
desired level of assurance that the auditor desires that the results of
the tolerable rate of deviation is the sample are in fact indicative of the
not exceeded by the actual rate actual incidence of deviation in the
of deviation in the population population, the larger the sample size
needs to be.

5. An increase in the number of Negligible effect For large populations, the actual size of
sampling units in the population the population has little, if any, effect on
sample size. For small populations
however, audit sampling may not be as
efficient as alternative means of
obtaining sufficient appropriate audit
evidence.
 Examples of Factors Influencing Sample Size for
Tests of Details

EFFECT ON
FACTOR SAMPLE SIZE
1. An increase in the auditor’s Increase The higher the auditor’s assessment of
assessment of the risk of the risk of material misstatement, the
material misstatement larger the sample size needs to be. The
auditor’s assessment of the risk of
material misstatement is affected by
inherent risk and control risk. For
example, if the auditor does not perform
tests of controls, the auditor’s risk
assessment cannot be reduced for the
effective operation of internal controls
with respect to the particular assertion.
Therefore, in order to reduce audit risk
and will rely more on substantive
procedures. The more audit evidence
that is obtained from tests of details
(that is, the lower the detection risk),
the larger the sample size will need to
be.
 Examples of Factors Influencing Sample Size for
Tests of Details (continued…)
EFFECT ON
FACTOR SAMPLE SIZE
2. An increase in the use of Decrease The more the auditor is relying on other
other substantive procedures substantive procedures (tests of details
directed at the same assertion or substantive analytical procedures) to
reduce to an acceptable level the
detection risk regarding a particular
population, the less assurance the
auditor will require from sampling and,
therefore, the smaller the sample size
can be

3. An increase in the auditor’s Increase The greater the level of assurance that
desired level of assurance that the auditor requires that the results of
tolerable misstatement is not the sample are in fact indicative of the
exceeded by actual actual amount of misstatement in the
misstatement in the population population, the larger the sample size
needs to be.

4. An increase in tolerable Decrease The lower the tolerable misstatement,

misstatement the larger the sample size needs to be
 Examples of Factors Influencing Sample Size for
Tests of Details (continued…)

EFFECT ON
FACTOR SAMPLE SIZE
5. An increase in the amount of Increase The greater the amount of
misstatement the auditor misstatement the auditor expects to find
expects to find in the population in the population, the larger the sample
size needs to be in order to make a
reasonable estimate of the actual
amount of misstatement in the
population. Factors relevant to the
auditor’s consideration o the expected
misstatement amount include the extent
to which item values are determined
subjectively, the results of tests of
control, the results of audit procedures
applied in prior periods, and the results
of other substantive procedures.
 Examples of Factors Influencing Sample Size for
Tests of Details (continued…)
EFFECT ON
FACTOR SAMPLE SIZE
6. Stratification of the Decrease When there is a wide range (variability) in the
population when monetary size of items in the population, it may
appropriate be useful to stratify the population. When a
population can be appropriately stratified, the
aggregate of the sample sizes from the strata
generally will be less than the sample size that
would have been required to attain a given level
of sampling risk, had one sample been drawn
from the whole population.

7. The number of Negligible effect For large populations, the actual size of the
sampling units in the population has little, if any, effect on sample size.
population Thus, for small populations, audit sampling is
often not as efficient as alternative means of
obtaining sufficient appropriate audit evidence.
(However, when using monetary unit sampling,
an increase in the monetary value of the
population increase in materiality for the financial
statements as a whole (and, if applicable,
materiality level or levels for particular classes of
transactions, account balances or disclosures.)
 Evaluation of Sample Results

Having carried out, on each sample item, those audit procedures that
are appropriate to the particular audit objective, the auditor should:

Analyze any error detected in the sample,

Project the errors found in the sample to the population, and

Assess the sampling risk.

 Conclusion
Having evaluated the sampling result, the auditor should
conclude as to the extent to which he has obtained
sufficient appropriate audit evidence in support of the
particular characteristic of the account balance or class
of transaction with which he is concerned.
 Detailed Audit Sampling Plans
Audit Sampling

Attributes Sampling in Variables Sampling in

Tests of Control Substantive Tests of Details

Statistical Nonstatistical Statistical Nonstatistical

Regular Sequential Probability

or Discovery or Proportional Classical
Classical Stop or Go To Size

Mean
Difference Ratio
per Regression
Estimation Estimation
unit
 Definition/Description of Audit Sampling Plans
Attribute Sampling Plan
This is used to test an entity’s rate of deviation (also called rate of occurrence) from a prescribed control
procedure. It is an audit sampling in which auditors look for the presence or absence of a control condition.

Variables Sampling Plan

This is used to test whether recorded account balances are fairly stated. For example, an auditor might use
a variables sampling plan to test recorded peso amounts for receivables, inventory, fixed asset additions
among others.

Statistical Sampling Plan

This is a sampling technique in which an auditor uses the laws of probability to select and evaluate a
sample. When using statistical sampling, auditors must select a random sample, which means every item
in the population must have an equal chance of being included in the sample.

Nonstatistical Sampling Plan

These plans rely exclusively on subjective judgment to determine sample size and to evaluate sample
results.

Regular or Classical Attributes Sampling

This sampling plan enables the auditor to estimate the rate of occurrence of certain characteristics in the
population. For example, the auditor might use this plan to estimate the percentage of cash disbursements
processed during the year that were not approved.
 Definition/Description of Audit Sampling Plans
(continued…)

Mean-per-unit Estimation
This is a classical variables sampling plan enabling the auditors to estimate the average peso value (or
other variable) of items in a population by determining the average value of items in a sample.

Difference Estimation
This is a sampling plan that uses the difference between the audited (correct) values and book values of
items in a sample to calculate the estimated total audited value of the population. Difference estimation
is used in lieu of ratio estimation when the differences are not nearly proportional to book value.

Ratio Estimation
This is a sampling plan that uses the ratio of audited (correct) values to book values of items in the sample
to calculate the estimated total audited value of the population. Ratio estimation is used in lieu of difference
estimation when the differences are nearly proportional to book values.

Regression
The regression approach is similar to the difference and ratio approaches. This approach has the effect of
using both the average ratio and the average difference in calculating an estimate of the total amount
for the population.
 Definition/Description of Audit Sampling Plans
(continued…)
Discovery Sampling
This form of attributes sampling is designed to locate at least one deviation (exception) in the population.
Discovery sampling is often used in situations in which the auditors expect a very low rate of occurrence
of some critical deviation. The purpose of a discovery sample is to detect at least one deviation, with a
predetermined risk of assessing control risk too low, if the deviation rate in the population is greater than
the specified tolerable deviation rate.

Sequential (Stop or Go) Sampling

This is a sampling plan for which the sample is selected in several steps, with the need to perform each
step conditional on the results of the previous steps. That is, the results may either be so poor as to
indicate that the control may not be relied upon, or so good as to justify reliance at each step.

Probability Proportional to Size (PPS)

This technique, which is also referred to as peso-unit sampling, applies attributes sampling theory to
develop an estimate of the total peso amount of misstatement in a population. Probability-proportional-to-
size sampling is used as an alternative to classical variable sampling methods for performing substantive
tests of transactions or balances.

Classical Variables Sampling Models

These use normal distribution theory to evaluate selected characteristics of a population on the basis of a
sample of the items constituting the population. These sampling applications provide the auditors with an
estimate of a numerical quantity such as the peso balances of an account. This technique is primarily
used by auditors to perform substantive tests.