AUDIT SAMPLING

CHAPTER 9
LEARNING OBJECTIVES
1. Define audit sampling
2. Explain the different risk considerations in
obtaining audit evidence
3. Differentiate statistical from non-statistical
sampling
4. Discuss sampling approaches and other means of
testing
5. Illustrate sampling for tests of controls and
substantive tests
6. Discuss the common projection techniques for
sampling in substantive tests
WAYS OF SELECTING ITEMS TO TEST

1. 100% examination
examine the entire population
Unlikely for test of controls
When a population constitutes a small number of
large value items when there is a significant risk
WAYS OF SELECTING ITEMS TO TEST
2. Selecting specific items
selection of specific item from a population
based on the auditors understanding of the
entity, assessed risk of material misstatement and
characteristics of being tested
Specific items include:
High value or key items
All items over a certain amount
Items to obtain information
Items to test control activities
WAYS OF SELECTING ITEMS TO TEST

3. Audit Sampling
The application of audit procedures to less than
100% of the items within an account balance or
class of transactions that all sampling units have
a chance of selection
AUDIT SAMPLING IN RELATION TO AUDIT PROCEDURES

RISK
ASSESSMENT
PROCEDURES
TESTS OF CONTROL
- Normally does
- Generally
not make use of
appropriate when
audit sampling
application of control
leaves audit evidence
of performance

SUBSTANTIVE PROCEDURES
- Relate to test of details only
TERMINOLOGIES USED IN AUDIT SAMPLING

ERRORS

DEVIATION MISSTATEMENT

Related to TOC Related to ST

Difference between Difference between the
what was expected and amount computed by
what actually occurred the auditor and amount
actually recorded in the
accounting records
TERMINOLOGIES USED IN AUDIT SAMPLING

TOTAL ERROR Rate of deviation or

total misstatement

EXPECTED ERROR Error that the auditor

expects to be present in
the population

ANOMALY Error that arises from an isolated

event that has not recurred other
than on specifically identifiable
occasions and is not
representative of the population
TERMINOLOGIES USED IN AUDIT SAMPLING

POPULATION Entire set of data from which

sample is selected and about which
the auditor wishes to draw
conclusions

SAMPLING UNITS Individual items

constituting a
population
 RISK OF MATERIAL MISSTATEMENT

Inherent Risk Control Risk

DETECTION RISK

SAMPLING RISK NON-SAMPLING RISK

SAMPLING RISK

Uncertainties related to sampling

Arise from possibility that the auditors conclusion,
based on a sample, may be different from the
conclusion reached if the entire population were
subjected to the same audit procedure
Result from the fact that a particular audit sample
may not be representative of the population tested
 How can we
lower down the
sampling risk?

By increasing the sample size

By using an appropriate
sample selection method
NON- SAMPLING RISK

Uncertainties arising from factors unrelated to

sampling
Includes the possibility of selecting audit procedures
that are not appropriate to achieve the audit
objectives
Human error or failure to detect errors contained in
the sample items or overlooking or misinterpreting
errors
 How can we reduce
the non- sampling
risk?
By proper planning and
supervision
By encouraging firm-wide
quality control
SAMPLING RISK IN TESTS OF CONTROLS
RISK OF ASSESSING RISK OF ASSESSING
CONTROL RISK TOO HIGH CONTROL RISK TOO LOW
(Risk of Underreliance) (Risk of Overreliance)
(Alpha or Type I Error) (Beta or Type II Error)
Risk that a sample deviation Risk that a sample does
rate supports assessing support assessing control risk
control risk at the maximum below the maximum when,
when, unknown to the unknown to the auditor, the
auditor, the true deviation true deviation rate in the
rate in the population population supports assessing
supports assessing control risk at the maximum
risk below the maximum Results in under-auditing
Results in Over-auditing Affects audit effectiveness
Affects audit efficiency
SAMPLING RISK IN SUBSTANTIVE TESTS
RISK OF INCORRECT RISK OF INCORRECT
REJECTION ACCEPTANCE
(Alpha or Type I Error) (Beta or Type II Error)
Risk that a sample supports Risk that a sample supports
the conclusion that a the conclusion that a
recorded account balance is recorded account balance is
materially misstated when, not materially misstated
unknown to the auditor, the when, unknown to the
account is NOT materially auditor, the account is
misstated materially misstated
Affects audit efficiency Affects audit effectiveness
GENERAL APPROACHES TO AUDIT SAMPLING

STATISTICAL SAMPLING NON-STATISTICAL SAMPLING

Sampling approach Sampling approach that

that uses: uses:
Random based selection Purely auditors
of sample judgment in estimating
The law of probability to risks, determining
measure sampling risk sample size, evaluating
and evaluate sample sample results
results
Allows the auditor to
measure or quantify
sampling risks
BENEFITS OF STATISTICAL SAMPLING

Design and efficient sample

Measure the sufficiency of evidence obtained
Objectively evaluate the sample results

DRAWBACK OF STATISTICAL SAMPLING

Additional costs of training audit staff, designing

sampling plans and selecting items for
examination
 AUDIT SAMPLING PLANS

ATTRIBUTE VARIABLE
SAMPLING SAMPLING
Used to estimate the Used to estimate the
frequency of occurrence numerical measurement
of a certain of a population such as
characteristic in a peso value
population (occurrence Used when performing
rate) ST to estimate the
Used when performing amount of
TOC to estimate the rate misstatements in the FS
of deviations from
internal control policies
 Define the objective

Determine the procedure

Determine the sample size

Select the sample

Apply the procedures

Evaluate the results

I. Define the objective of the test
Objectives determine the audit procedures to
be applied
II. Determine the audit procedure to be performed
Specific procedures to satisfy the objective
III. Determine the sample size
Auditor must decide how many sampling
units to include in the sample in which the
audit procedures will be applied
IV. Select the sample
Sample selection technique must be
designed in a way that all items in the
population have equal chances of being
selected
V. Apply the procedures
After sample items have been selected, appy
the procedures to the sample.
VI. Evaluate the sample results
Evaluate the results to determine whether
sufficient evidence has been obtained to
satisfy the audit objective
 Define the objective

Determine the procedure

Determine the sample size

Select the sample

Apply the procedures

Evaluate the results

SAMPLING FOR TESTS OF
CONTROLS
SAMPLING FOR TESTS OF CONTROLS

Controls without documentary

evidence of performance
Acceptable
Sampling
Risk
DETERMINE
THE
SAMPLE SIZE

Tolerable
Deviation
Rate
ACCEPTABLE SAMPLING RISK
POPULATION POPULATION
Not chose
Not as Sample
Chosen 20%
as
Sample Sample
Sample 40% 80%
60%

Not chose as Sample Sample

Size of the sample is affected by the level of

sampling risk the auditor is willing to accept.
Acceptable sampling risk and sample size are
inversely related.
TOLERABLE DEVIATION RATE
Maximum rate of deviations the auditor is willing
to accept, without modifying the planned degree
of reliance on the internal control
Establishing TDR and ASR requires professional
judgment and involves consideration of:
1. The importance of control
2. Degree of reliance placed on such control

Tolerable deviation rate and sample size are

inversely related.
TOLERABLE DEVIATION RATE

Control Acceptable Tolerable Sample Size

(in providing Level of Deviation
reliable FS) Sampling Rate
Risk
Important Low Low More
Not so High High Less
important
EXPECTED DEVIATION RATE
Rate of deviations the auditor expects to find in
the population before testing begins
Expectations could be based on the prior years
results or by examining few items in the
population (pilot sample)

Expected deviation rate and sample size are

directly related.
Expected deviation rate should NOT EXCEED
the tolerable deviation rate. Otherwise, assess
the control risk at HIGH LEVEL
Sample Size Acceptable Tolerable Expected
Level of Deviation Deviation
Sampling Rate Rate
Risk
Small High High Low
Large Low Low High
TOC- SAMPLE SELECTION METHOD
RANDOM NUMBER SELECTION
Auditor selects sample by matching random
numbers, generated by a random number table or
a computer software generator, with the
population numbering system such as document
number

ADVANTAGE
Gives each item in the population an equal
opportunity to be selected
Useful for statistical and non-statistical sampling
RANDOM NUMBER SELECTION

Random Number Purchase Order Number

5 1000
1 1001
9 1002
10 1003
4 1004
6 1005
2 1006
3 1007
7 1008
8 1009
SYSTEMATIC SELECTION
Auditor determines a constant sampling interval and
then selects the sample based on the size of that
interval
Auditor should determine that the population is not
structure in such manner that the sampling interval
corresponds with a particular pattern in the
population

ADVANTAGE
Easy to use
Population items do not have to be pre-numbered
in order for the auditor to use this
Useful for statistical and non-statistical sampling
SYSTEMATIC SELECTION
Population name: Purchase Order
Population Size: 20
Sample Size needed: 10
Random Starting point: Item No. 3

SAMPLING INTERVAL = POPULATION / SAMPLE SIZE

2 = 20/10

Randomly selects the starting point

No. Purchase Order Number
1 1000
2 1001
1. 3rd PO (random start point)
3 1002 2. 5th PO=3rd + 2 (SI)
4 1003 3. 7th PO= 5th +2
5 1004 4. 9th PO= 7th +2
6 1005 5. 11th PO= 9th +2
7 1006 6. 13th PO= 11th + 2
7. 15th PO= 13th + 2
8 1007
8. 17th PO= 15th +2
9 1008 9. 19th PO= 17th +2
10 1009 10. 1st PO= 19th +2
11 1010
12 1011
13 1012
14 1013
15 1014
16 1015
17 1016
18 1017
19 1018
20 1019
HAPHAZARD SELECTION

Sample is selected without following an organized

or structured technique
Best for non-statistical sampling
BLOCK SELECTION

Selecting a group of items arranged contiguously

within a larger grouping of sampling units
Least desirable sample selection method

DRAWBACKS
Results excessively high sampling risk
Testing large number of blocks is inefficient
 What
if?
Voided Documents
If it is properly voided, it
should be replaced by another
sample item

Missing documents
Auditor was not able to
determine whether the control
was properly performed, such
item should be treated as
deviation
EVALUATION OF RESULTS
EVALUATION OF RESULTS
TEST OF CONTROLS

1. Determine
the sample
deviation
rate

Number of deviations/ sample size

 EVALUATION OF RESULTS
TEST OF CONTROLS

2. Compare the sample

deviation rate with the
tolerable deviation rate and
draw an overall conclusion
about the population.

Sample deviation rate Sample deviation rate is

exceeds the tolerable less than the tolerable
deviation rate deviation rate
Control risk will be assessed Consider the allowance for
at a high level and more sampling risk
extensive ST should be
performed
 EVALUATION OF RESULTS
TEST OF CONTROLS

ALLOWANCE FOR SAMPLING RISK

Possibility that sample results could have occurred
even if the actual population deviation rate is
higher than the tolerable rate
 EVALUATION OF RESULTS
TEST OF CONTROLS
a. Sample deviation rate b. Sample deviation rate is barely
is considerably lower lower than the tolerable rate
than the tolerable rate Non-Statistical sampling: auditor
concludes that the sample results
Auditor can safely do not justify his preliminary
assessment of CR
assume that the
Statistical Sampling: auditor
sample results determines the maximum
supported the planned population deviation rate by
multiplying a sampling table or
degree of reliance on statistical formula
internal control If the maximum population
deviation rate exceeds the
tolerable deviation rate, assess CR
at high.
OTHER SAMPLING APPLICATIONS FOR TOC

SEQUENTIAL SAMPLING (STOP-OR-GO SAMPLING)

Can be used when the auditor expects very few deviations
within the population
After testing a sample, the auditor makes a decision of
whether to stop or go on with the sampling plan

DISCOVERY SAMPLING
Most appropriate when no deviations are expected in the
population, thus even ONE deviation would cause concern
When auditor suspects that an irregularity might have been
committed
SAMPLING FOR SUBSTANTIVE
TESTS
FACTORS IN DETERMINING THE SAMPLE SIZE

1. Acceptable Sampling Risk

Size of the sample is affected by the level of

sampling risk the auditor is willing to accept.
Acceptable sampling risk and sample size are
inversely related.
FACTORS IN DETERMINING THE SAMPLE SIZE

2. Tolerable misstatement
Maximum amount of misstatement that the auditor
will permit in the population and still be willing to
conclude that the account balance is fairly stated
Determined in the planning stage of audit
Related to the auditors preliminary estimate of
materiality

Tolerable misstatement and sample size are

inversely related.
FACTORS IN DETERMINING THE SAMPLE SIZE

3. Expected Misstatement

Amount of misstatement that the auditor believes

exists in the population

EXPECTED misstatement and sample size are

DIRECTLY related.
FACTORS IN DETERMINING THE SAMPLE SIZE

4. Variation in the Population

When a population consists of highly variable

recorded amounts, it is difficult to select a
representative sample
Variability can be estimated by the auditor based on
the prior years tests results or pilot sample.

Larger sample size is required as the degree of

variability within the population increases
ST- SAMPLE SELECTION METHOD

Aside from the sample selection methods discussed in

the Test of Controls, here are two additional methods:
STRATIFIED SAMPLING

Auditor may divide or stratify the population into

meaningful groups in order to decrease the effect
of variance within the population
Sample size should be determined for each
stratum and selected from that stratum

ADVANTAGES
Decreases the effect of variance in the population
thus decreases sample size
Allows the auditor to give more emphasis to those
items with higher monetary value
STRATIFIED SAMPLING

STRATUM ACCOUNT NO. OF SAMPLE SIZE

BALANCES CUSTOMERS
1 > P1,000,000 40 100%
Examination
2 P100,000 to 170 50 customers
P1,000,000
3 < P100,000 2,040 100
customers
VALUE WEIGHTED SELECTION
(PROBABILITY PROPORTIONAL TO SIZE SAMPLING)
(MONETARY UNIT SAMPLING)
Probability of an item to be selected is directly
proportional to the monetary value of such item
Each peso is treated as one sampling unit

Large monetary values are given greater representation

in the sample
Appropriate when the auditor expects overstatement
errors because the greater the overstatement, the
greater the probability that the account will be selected
and the overstatements detected
VALUE WEIGHTED SELECTION
(PROBABILITY PROPORTIONAL TO SIZE SAMPLING)
(MONETARY UNIT SAMPLING)
Whats the
Population name: Accounts Receivable
probability
Total Population Amount: P1,000,000
that it will
Account balance of one customer is
P100,000 be chosen as
a sample?

P100,000 / 1,000,000 = 10%

CPA
EVALUATION OF RESULTS
 I. PROJECT THE MISSTATEMENTS TO THE POPULATION

Identified misstatements pertain to the sample

only.
Auditor should project these misstatements to the
population to determine whether the account
balance is materially misstated
Anomalous errors should be excluded when
projecting sample errors
METHODS OF PROJECTING MISSTATEMENTS:
1. Ratio Estimation
2. Difference estimation
3. Mean-per-unit estimation
RATIO ESTIMATION
Projected misstatement is determined by
multiplying the portion of sample amount
misstated times the total recorded population
book value
Appropriate to use when the misstatement is
directly proportional to its book value

Projected Misstatement
= Amount of misstatement x (Population BV / Sample BV)
DIFFERENCE ESTIMATION
Used to measure the estimated total misstatement
amount in the population when there is both a
recorded value and an audited value for each item in
the sample
Appropriate when the misstatement in an account is
not affected by the book value of the item being
examined
Projected Misstatement
= Amount of misstatement x (Population Size / Sample size)
MEAN-PER-UNIT ESTIMATION

Auditor is concerned with the audited value rather

than the misstatement amount of each item in the
sample
Appropriate when individual populations do not have
recorded values

Estimated Population Audited Value

= Average or mean AV x No. of items in population

AV / population size
ILLUSTRATION

Auditor sent out confirmation requests to verify the

validity of the accounts receivable. The following
data are given:

In terms of In terms of Amount of

Value No. of Misstatements
customers found
Population P10,000,000 200 ?
Sample P1,000,000 24 P48,000
RATIO ESTIMATION
PM= P48,000 * (P10,000,000/ P1,000,000)
PM= P480,000

DIFFERENCE ESTIMATION
PM= P48,000 * (200/ 24)
PM= P400,000
II. COMPARE THE PM TOGETHER WITH THE TOLERABLE
MISSTATEMENTS AND DRAW AN OVERALL CONCLUSION

If PM > the TM, auditor will conclude that the

account balance is materially misstated
In this case, the auditor may:
1. Examine additional units
2. Perform suitable alternative procedures
3. Request client to adjust the account balance
II. COMPARE THE PM TOGETHER WITH THE TOLERABLE
MISSTATEMENTS AND DRAW AN OVERALL CONCLUSION

If PM < the TM, auditor should consider the

allowance for sampling risk.
The auditor should recognize that sampling risk
increases as the PM approaches the TM.