CHAPTER ONE

Audit Sampling

Chapter Objectives

At the end of this chapter, students will be able to:

Define audit sampling
Identify the type of audit procedures that do not involve audit sampling
Distinguish between sampling risk and non-sampling risk
Discuss the different types of audit sampling design
Apply statistical and non-statistical sampling methods to tests of controls and substantive tests.

Audit testing procedures refer to both (i) selective examination procedures and (ii) audit sampling.
I. SELECTIVE EXAMINATION

Selective examination refers to the identification and selection by the auditor (for subsequent examination) of
certain items, usually key items, from a particular population.
For example, in the audit of an account balance, the auditor may decide to select (for subsequent vouching)
all items making up the account balance greater than $x; or, in the audit of a receivables account balance,
an auditor may decide to select (for subsequent positive confirmation) all customers with account balances
older than y months.
The selection of these items is not audit sampling but is referred to as selective examination. Selective
examination is a form of audit testing, but not a form of audit sampling as, for example, a conclusion
cannot be drawn, based on the items selected, about the population as a whole.
Where an auditor vouches every item in a population (as is often the case with small populations in which
knowledge of the existence of exceptions is critical to the auditor's opinion about the population); it is
referred to as a 100% examination. This is not a form of audit testing.

II. AUDIT SAMPLING

Nature of Audit Sampling

Sampling refers to the process of selecting a group of items from a large group of items. The assumption of
sampling is that the sample is the representative of the population.
Audit sampling refers to the application of an audit procedure to less than 100% of the items within an
account balance and class of transactions for the purpose of evaluating some characteristic of the balance
or class.
Auditors may encounter two types of risk in evidence gathering process:
1. Sampling risk:
the possibility that the sample drawn is not representative of the population and, as a result, the
auditor will reach an incorrect conclusion.
Is a function of sample size. The larger the sample size, the lower the sampling risk and vice versa.
can be quantified using statistical sampling.
can be reduced by increasing sample size
Key issue: balance sampling risk with the cost of using large sample
Reducing Sampling Risk Adjust sample size, Use appropriate method for
selecting sample items. Note: A 95% confidence level = 5% sampling risk.
Sampling risk is an inherent part of sampling that results from testing less
than the entire population.

1
 2. Non-sampling risk: the possibility that the auditor uses inappropriate audit procedures, fail to detect a
misstatement when applying an audit procedure, or misinterpret an audit result. It can not be quantified
using statistical sampling. The uncertainty related to such risk can be controlled by:
Adequate training
Proper planning
Effective supervision
Reducing Non-sampling Risk Careful design of audit procedures, proper
instruction, supervision, and review.
Audit sampling is needed for audit test. However, all audit tests do not involve audit sampling. Which
audit tests do not involve sampling?

Audit Tests that do not involve sampling

a. Inquiry and Observation
Are used extensively as a source of evidential matter such as:
To understand the components of internal control
To evaluate many of the inherent risk factors
To establish the existence of some items
Reviewing records for the method of accounting and other information.
Observing accounting procedures.
Discussing methods of accounting and reporting with the client.
Scanning documents for possible issues.
b. Analytical review procedures
Especially simple analytical procedures such as simple comparisons and ratio analysis
Comparing records reports and other information.
Re computing or estimating amounts.
Reviewing trends in reporting.
Comparing similar businesses.
c. Procedures applied to every item in the population/One Hundred Percent Examination
Reviewing all fixed asset purchases, where appropriate.
Examining all contracts, where there are a small number.
Reconciling items.
d. Classes of transactions or account balances not tested/ Zero Percent Examination
Because of an acceptably low risk of material misstatement or immateriality
e. Tests of automated information technology controls

Type I and Type II Errors

A. In relation to tests of controls
1. Type I Error (alpha)
The risk that the assessed level of control risk based on the sample is greater than the true
operating effectiveness of the control (assessed risk beyond the truth).
Risk of assessing control risk too high
2. Type II Error (beta)
The risk that the assessed level of control risk based on the sample is less than the true operating
effectiveness of the control (assessed risk below the truth).
Risk of assessing control risk too low
B. In relation to substantive tests
1. Type I Error (alpha)
The risk that the sample supports the conclusion that the recorded account balance is materially
misstated when it is not materially misstated
2
 Risk of incorrect rejection
Relates to the efficiency of the audit (more audit work than necessary)
2. Type II Error (beta)
The risk that the sample supports the conclusion that the recorded account balance is not
materially misstated when it is materially misstated
Risk of incorrect acceptance
Relates to the effectiveness of the audit (less audit work than necessary and may lead to litigation
against the auditor)

Allowance for Sampling Risk (Precision)

Precision measures the closeness between a sample estimate and the population characteristic being
estimated.
Allowance for sampling risk (AFSR) is the uncertainty that results from sampling. It is the difference
between the expected mean of the population and the tolerable deviation or misstatement.
Allowance for sampling risk is the range set by + and - limits from the sample results within which the
true value of the population characteristics being measured is likely to lie.
Example:
1. Suppose an auditor expects that a control would have a 3% deviation (failure) rate and s/he was willing
to tolerate a deviation rate of 5%, the allowance for sampling risk would be 2% (i.e. 5% - 3% = 2%).
2. Assume the auditor tested 50 items and found one deviation, the sample deviation rate is 2% (i.e. 1/50 =
0.02). If the upper tolerable limit is 3.5%, the allowance for sampling risk would be 1.5%.

Types of Audit Sampling

1. Non-statistical (or Judgmental) sampling
The auditor considers sampling risk when evaluating the results of an audit sample without using
statistical theory to measure sampling risk
Requires the auditors professional judgment to plan, perform, and evaluate the sample evidence.
Limitation: may not be as effective as statistical sampling.
2. Statistical Sampling
Uses the laws of probability to select and evaluate the result of audit sample
Helps the auditor:
Design an efficient sample
Measure the sufficiency of evidence obtained
Quantify sampling risk
Limitations (drawbacks):Involve additional costs of:
Training auditors in the proper use of sampling techniques
Designing and conducting the sampling application
Three major types of statistical sampling plans may be used:
a. Attribute sampling
Used to estimate the proportion of population that possesses specific characteristic.
"Attribute sampling" is used when the auditor is only concerned with
acceptance or rejection of a hypothesis. It is used to reach a yes or no
answer about a question.
Is commonly used for tests of controls
b. Monetary-Unit Sampling (MUS) percentage of monetary units/overstatements issues
Uses attribute sampling theory and techniques to estimate the birr amount of misstatement for a
class of transactions or an account balance.
designed to test for overstatements
Its sampling unit is individual Dollar (Birr)
3
 is important for auditing accounts receivable, loans receivables, investment securities, and
inventory
estimates the percentage of monetary units in a population that might be misstated and then
multiplies this percentage by an estimate of how much the dollars are misstated.

c. Classical Variables Sampling (CVS) transaction issue (overstatements + understatements)

Used to determine if a class of transactions or account balance is materially misstated and aims
at the rate of misstatement.
"Variables sampling" is used to reach a conclusion about a population in
terms of an amount. Variables sampling is commonly used to determine the
dollar/birr size of a population or to determine if the stated dollar /birr size is
correct.
Uses normal distribution theory to evaluate the characteristics of a population based on sample
data. Auditors most commonly use classical variables sampling to estimate the size of
misstatement
Its sampling unit is each transaction or account balance
Advantages of CVS:
1. The techniques are effective for both overstatements and understatements.
2. The selection of zero balances generally does not require special sample design
considerations.
I. STATISTICAL VS. NONSTATISTICAL SAMPLING
Audit sampling may be performed using either statistical or non-statistical techniques
Statistical techniques require (i) the units in the population to have the same chance of
being selected (ii) the items for examination to be selected randomly and (iii) the
conclusion to be drawn using tables or formulas based on probability theory.
Statistical Sampling uses the laws of probability to select and evaluate the result of audit
sample.
Non-statistical Sampling (or Judgmental Sampling) estimates sampling risk by using
professional judgment rather than using by statistical techniques.
Similarities
Both sampling approaches require the exercise of auditor judgment during the planning,
implementation and evaluation of the sampling plan.
In other words, the use of statistical methods does not eliminate the need to exercise
judgment.

Differences
Statistical sampling allows the user to measure and control the sampling risk associated
with the procedure.
Statistical sampling applies the laws of probability to determine the percent likelihood that
the sample does not accurately reflect the population.
In nonstatistical sampling those items that the auditor believes will provide the most useful
information are selected. Conclusions are judgmental = judgmental sampling

Limitation
Statistical sampling: Involves additional costs of training auditors in the proper use of
sampling techniques- designing and conducting the sampling application.
Non-Statistical sampling May not be as effective as statistical sampling.

II. PROBABILISTIC VERSUS NONPROBABILISTIC SAMPLE SELECTION

4
Probabilistic Sample Selection Selecting a sample such that each population item
has a known probability of being included in the sample and the sample is selected by a
random process.
Non-probabilistic Sample Selection Selecting a sample in which the auditor uses
professional judgment rather than probabilistic methods to select sample items.

Non-probabilistic Sample Selection methods include:

1. Directed Sample Selection
Also known as judgment sample selection is based on the auditor's sound and
seasoned judgmental criteria. Three basic issues determine which items are selected:
Items most likely to contain misstatements-relative risk
Items containing selected population characteristics-representativeness
Large dollar coverage-value of the item

2. Block Sample Selection

Selection of several items in sequence forming blocks of items
For example, all remittances in the month of November. Alternatively, remittances 300-350
may be examined in their entirety.
Block selection should be used with caution because valid references cannot be made
beyond the period or block examined.
If block sampling is used, many blocks should be selected to help minimize sampling risk.
3. Haphazard Sample Selection
Selection without regard to size, source, or distinguishing characteristics (without bias)
It represents the auditor's best estimate of a representative sample -- and may, in fact, be
representative.
Defined probability concepts are not employed. As a result, such a sample may not be used
for statistical inferences.
The problem with this method is that it does not avoid unconscious bias.

Probabilistic Sample Selection methods include:

4. Simple Random Sample Selection
Every possible combination of elements in the population has an equal chance of
constituting the sample.
An auditor can implement simple random sampling in one of two ways: computer programs
to generate random numbers or uses random number tables.
5. Systematic Sample Selection
The auditor calculates an interval and then selects the items for the sample based on the
size of the interval.
The interval is determined by dividing the population size by the number of sample items
desired.
If this method is used, auditors ensure that the listing of the items in the population is
ordered in some way; otherwise the selection of items may be biased.
Example
Population of sales invoices 652 3151
Desired sample size = 125
Interval = (3151 651) / 125 = 20
Select a random start between 1 & 20 (ex. 9)
First item in sample is invoice # 661 (652 + 9)
Remaining 124 items = 681 (661+20), 701 (681+20), 721 (701+20) etc.
6. Probability Proportional to Size (PPS) Sample Selection
for emphasis on large dollar / birr items
A sample is taken where the probability of selecting any individual population item is
proportional to its recorded amount (PPS).
5
 Evaluated using monetary unit sampling

7. Stratified Sample Selection

For emphasis on large dollar items
The population is divided into sub populations by size and larger samples are taken of the
larger subpopulations.
Evaluated using variable sampling

STRATIFICATION EXAMPLE: Audit client A sells three types of computer equipment:

laptops, desktops and network servers. The auditor decides to stratify the total
population of sales by type of computer equipment, since that tends to create more
homogeneous sub-populations.
There were $2,000,000 total laptop sales during the period, $3,000,000 total desktop
sales and $5,000,000 server sales. The auditor should allocate the total sample size as
follows:
o 100 from laptop sales
o 100 from desktop sales
o 100 from network sales
The results were as follows:
o 5% under-reported laptop sales X $2,000,000 = $100,000
o 5% over-reported desktop sales X $3,000,000 = ($150,000)
o 10% under-reported network sales X $5,000,000 = $500,000
Remember, an essential feature of probability sampling methods is that each element of the
population being sampled has an equal chance of being included in the sample and, moreover,
that the chance of probability is known. Only in this way, is a probability sample representative
of a population.

Performance and Evaluation

Must address four issues:
a. The auditor must consider the effect of not being able to apply a planned audit procedure to a
sampled item
b. The auditor should project the sample results to the population being tested and compare those
results with the planned amounts
c. The auditor must give appropriate consideration to sampling risk
d. The auditor must adequately consider qualitative aspects of misstatements such as:
The nature and causes of misstatements
The possible relationship of the misstatement to other phases of the audit

Application of Audit (attribute) Sampling to Tests of Control

Attribute sample is concerned with one-sided test because the auditor is generally concerned with the maximum
deviation rate in the population.

Step 1: State the objectives of the audit test.

The objective is to evaluate the operating effectiveness of internal control

Step 2: Define the control deviation conditions

A deviation is a departure from adequate performance of the internal control

It is necessary to clearly define the situation in which deviation occurs.
6
 Eg. Lets say the objective of the test is to check whether purchase invoice was approved by the finance
manager before being recorded. A purchase order which was not approved (no signature & stamp) by the
finance manager is considered deviation.

Step 3: Define the population & sampling units

Population: Population depends on the objective of the test. If the objective of the test is to check
whether purchase invoice was approved by the finance manager before being recorded, all purchase
orders received during the period are considered population. The auditor should ensure that the sample
frame is complete.
Sampling unit: Sampling unit refers to the individual members of the population. A sampling unit may
be a document, an entry or a line item. In the above example, the sampling unit is individual purchase
invoice.

Step 4: Determine the sample size

Factors to be considered in determining the sample size:

1. Determining the acceptable risk of assessing control risk too low
the risk that the sample will support the auditor's planned degree of reliance on the control when the
true deviation rate for the population does not justify such reliance (type II error)
Its determination is primarily based on the auditors professional judgment
the auditor should consider the importance of the audit objective
There is an inverse relationship between the risk of assessing the control risk too low and sample
size
The smaller the acceptable risk of assessing control risk too low, the larger the sample size must be.
Factors to be considered in setting the acceptable risk of assessing control risk too low:
a. Effectiveness concern
b. Efficiency concern

2. The tolerable deviation rate

the maximum deviation from a prescribed control that the auditor is willing to accept without altering
the planned assessed level of control risk
The suggested tolerable deviation rates for assessed levels of control risk

Planned assessed level of control risk Tolerable deviation rate

Low 3 - 7%
Moderate 6 - 12%
Slightly below maximum 11 - 20%
Maximum Omit test (undergo substantive tests)

The tolerable deviation rate is inversely related to the sample size

The lower the tolerable deviation rate, the larger the sample size
The concern of the auditor is whether the true deviation rate exceeds the tolerable deviation rate
There is direct relationship between the planned assessed level of control risk and tolerable deviation
rate
3. The expected population deviation rate
is the deviation rate that the auditor expects to exist in the population
can be developed based on prior years' results, paste experience from similar tests on other
engagements, or on a pilot sample
The expected population deviation rate has a direct relationship to sample size.
7
 The larger the expected population deviation rate, the larger the sample size must be.
If the auditor believes that the expected population deviation rate exceeds the tolerable deviation rate,
the statistical test should be omitted and substantive tests should be used.

The effect of Sample Selection Factors on Sample Size

Factors Relationship to Examples
sample Change in Factor Effect on Sample
Acceptable risk of assessing Lower Increase
control risk too low Inverse Higher Decrease
Tolerable Deviation rate Inverse Lower Increase
Higher Decrease
Expected Population deviation Direct Lower Decrease
rate Higher Increase

Once the above three factors are determined, the appropriate sample size is determined from the table shown on
the following page:

8
Step 5: Determine sampling method and Select the sample
Once the sample size is determined, the sample will be selected using the appropriate techniques

Step 6: Perform the audit procedures/Test the sample items/

In conducting the planned audit procedures, the following are not considered deviation
properly Voided documents
Unused or inapplicable documents
If the auditor is unable to examine a sampled item, the sample item is considered a deviation
If a large number of deviations are detected early in the tests of controls, the auditor should consider stopping
the test because the result of the test will not support the planned assessed level of control risk

Step 7: Evaluate the Sample Result

1. Calculate the sample results
involves summarizing the deviations by the controls tested and evaluating the results
involves calculating the sample deviation rate and the computed upper deviation rate
a. Sample deviation rate
is the number of deviations in the sample divided by the number of items in the sample
represents the auditor's best estimate of the population's deviation rate. However the auditor must
consider allowance for sampling risk
b. Computed upper deviation rate
is the sum of sample deviation rate and allowance for sampling risk
represents the upper limit for population deviation rate

2. Performing Error Analysis

involves evaluating the qualitative aspects of the deviations identified
Involves two considerations:
a. the nature of each deviation and its cause
Error or fraud?
Misunderstanding of instructions or carelessness?
b. the impact of the deviation on other phases of the audit

Step 8: Draw final conclusion

involves comparing the tolerable deviation rate to the computed upper deviation rate
If the computed upper deviation rate is less than or equal to the tolerable deviation rate, the auditor
can conclude that the controls can be relied on
If the computed upper deviation rate exceeds the tolerable deviation rate, the auditor may perform
the following:
1. Modify sample size
2. Modify tolerable deviation rate
3. Conclude that the controls are not operating at an acceptable level.
The auditor's professional judgment of the results of tests of control affects the final conclusion.
Step 9: Document the sampling Procedures
All steps performed so far should be documented in the auditors working papers

Application of Audit Sampling to Substantive Tests-Monetary Unit Sampling

Step 1: State the objectives of the audit test

9
 When auditors sample for tests of details of balances, the objective is to determine whether the account
balance being audited is fairly stated.
Sampling may be used for substantive testing to test the reasonableness of assertions about a financial
statement amount, and to develop an estimate of some amount.

Step 2: Define Misstatement Conditions

Misstatement conditions are any conditions that represent a monetary misstatement in a sample item.
A misstatement is defined as the difference between monetary amounts in the clients records and
amounts supported by audit evidence.
When the clients amount deviates from amount supported by audit evidence, misstatement is said to
occur. However, it may not be material in amount.
Step 3: Define the population and the sampling units
In testing for the existence objective, the recorded dollar population is the population.
For MUS the population is defined as the monetary value of an account balance, such as accounts
receivable, investment securities, or inventory
For MUS, an individual dollar represents the sampling unit. However, the auditor tests not individual
birr but rather the account or the transaction that contains the selected birr. The account balance or
transaction that contains the selected Birr is called the logical unit.

Step 4: Determine the sample size

Factors to be considered:
1. Variation within the population
Population variation and sample size have direct relationship in classical variables sampling.
As
Determination population
of sample sizevariation increases, the
for Monetary-Unit sample size should increase
Sampling:
Population
Attribute samplingvariation
table canCanbe be minimized by stratifying the population
used
Steps: Population variation does not affect the sample size when monetary unit sampling is used because
1. Determine
the sample the selection
risk for incorrect acceptance
method considers indirectly.
2. covert the tolerable misstatement and the expected misstatement to percentages of
2. Acceptable risk of incorrect acceptance (type II error)
book value
There is an inverse relationship between risk of incorrect acceptance and the sample size
3. Use attribute sample table
Thethe
Alternatively, lower the risk
sample sizefor
canincorrect acceptance,
be computed usingthethelarger the sample
following formula:size must be
3. Tolerable misstatement
nThe= tolerable BV XRFmisstatement is the amount of the preliminary judgment about materiality that is
allocated to(TM-(EM
an account x EF))
The tolerable misstatement is the maximum amount by which the account can be misstatement with
Where,
n = the auditor
sample sizestill accepting the account as being fairly Value
BV = Book presented
=
TM Tolerable
Tolerable misstatement
Misstatement is inversely relatedEMto=sample
Expectedsize.Misstatement
EF
The lower the amount of tolerable misstatement, the largerFactor
= Expansion Factor RF = Reliability the sample size must be.
*Expansion factor
4. Expected misstatement adjusts the expected misstatement for the risk of incorrect acceptance.
Example: Suppose the auditor has established a tolerable misstatement of Br. 250,000
The expected misstatement is the amount of misstatement that the auditor believes exists in the
and an expected misstatement of Br. 50,000 for an account receivable account with a book
valuepopulation.
of Br. 5,000,000. The risk of incorrect acceptance is 5% and the corresponding
The expected
reliability factor and misstatement
expansion can be (adjustment
factor developed based on the assessment
of expected misstatement of inherent risk,ofprior year's
for the risk
incorrect
results,acceptance)
a pilot sample, arethe
3.00 andof1.6
results respectively.
related substantiveNotetests,that the
or the reliability
results of testsfactor and
of controls.
expansion
There isfactor arerelationship
a direct obtained from relevant
between tables.
expected misstatement and sample size.
Tolerable misstatement rate = 250,000/5,000,000 = 0.05
The larger the expected misstatement, the larger the sample size must be
Expected misstatement = 10,000/5,000,000 = 0.01
5. Sample
Population
size size
(n)
Population
Sample size(n)
size is directly
= related to sample size
5,000,000 X3
The larger the population size, the larger the samplex size
(250,000-(50,000 1.6)must be.
n = 88

10
Step 5: select the sample items using systematic sampling method
For Monetary-Unit Sampling, (by applying systematic sampling method) probability-proportional-to-size
method is used, which gives each birr in the population an equal chance of being selected and divides the
population in to equal groups of birr. Each group of birr represents a sampling interval, which is obtained by
dividing the book value of the population by the sample size

Assume a clients book value of accounts receivable is Br.5,000,000, and the auditor determined a sample size of
88. The sampling interval will be Br. 56,818. The auditor randomly selects a number between 0 and 56,818, and
then select every 56,818th Birr to identify the balance to be included in the sample.

Step 6: Perform the audit procedures

After the sample items have been selected, the auditor conducts the planned audit procedures on the
logical units containing the selected dollar sampling units.

Step 7: Evaluate the sample results

1. Calculate the sample results
projecting the misstatement detected in the sample to the population (called misstatement limit),
which represents the mean misstatement in the population
calculating an allowance for sampling risk and add it to the projected misstatement in order to
determine the misstatement limit
2. Perform error analysis

Step 8: Draw final conclusions

Tolerable misstatement is compared to the sum of projected misstatement and allowance for sampling risk
(misstatement limit)
If the sum of projected misstatement and allowance for sampling risk is less than or equal to tolerable
misstatement, the auditor can conclude that the account is not materially misstated for the tested assertion

11
 The sum of projected misstatement and allowance for sampling risk is greater than tolerable misstatement,
the auditor can conclude that the account is materially misstated for the tested assertion. When faced with
this situation, the auditor may:
1. Increase the sample size.
2. Perform other substantive procedures.
3. Request the client adjust the accounts balance.
4. If the client refuses to adjust the account balance, the auditor would consider issuing a qualified or
adverse opinion.

Step 9: Document the sampling procedures

Illustration on Monetary Unit Sampling Method

The auditors wish to test the valuation of accounts receivable in the audit of ABC Company with the objective of
ascertaining whether the balance is fairly stated. The client has Br. 2,500,000 of total recorded receivables,
composed of 500 accounts. The auditors have determined the following:
Tolerable misstatement (error) Br. 50,000
Risk of incorrect acceptance 10% (Reliability Factor = 2.31)
Expected misstatement (error) Br. 20,000 (Expansion factor = 1.50)
The auditors have decided to use Probability-proportional-to-Size Sampling. Assume that the auditors have tested
the sample and discovered the following four misstatements:

Book value (BV) Audited Value (AV)

Br. 1000 920
4000 3500
5000 4800
9800 9000

Reliability factors for errors of overstatement (partial)

Number of Risk of incorrect Acceptance
overstatement errors 1% 5% 10%
0 4.61 3.0 2.31
1 6.64 4.75 3.89
2 8.41 6.30 5.33
3 10.05 7.76 6.69
4 11.61 9.61 8.00
5 13.11 10.52 9.28

Expansion Factors (EF) for expected error

Risk of Incorrect Acceptance
1% 5% 10% 15% 20% 25% 30% 37% 50%
EF 1.9 1.6 1.5 1.4 1.3 1.25 1.2 1.15 1.0

Required:
1. Compute the following:
a. the required sample size
b. sampling interval

12
 c. projected misstatement
d. Basic precision (min. allowance for sampling errors and misstatements)
e. Incremental allowance
f. Upper limit on misstatement
2. Draw final conclusion about the fairness of accounts receivable balance

Solution
1. Computations
a. Sample size = 2,500,000 x 2.31_____ = 289
50,000 (20,000 x 1.5)
b. Sampling interval = 2,500,000/289 = 8651
c. Projected misstatement:
Projected misstatement in the population is the sum of projected misstatement for each account
identified as misstatement. It can be computed by considering the following cases:
Case 1: When BV of the misstated account is less than the sampling interval
Projected misstatement = Tainting Percentage x Sampling interval
tainting percentage = the percent of misstatement in the account
= (BV AV) /BV
Case II: When BV of the misstated account is equal to or greater than the sampling interval
Projected misstatement = the actual misstatement in the account
= BV AV
Thus, total projected misstatement in the population = case 1 + case 2

BV Audited value Misstatement Tainting % Sampling Projected

interval misstatement
Br. 1000 920 80 0.08 8651 692
4000 3500 500 0.125 8651 1081
5000 4800 200 0.04 8651 346
9800 9000 800 NA NA 800
19,800 18,220 1580 2919

d. Basic precision = Reliability factor X sampling interval

= 2.31 x 8651 = 19,984
*Basic precision is the minimum allowance for sampling risk, given no errors or misstatements
e. Incremental allowance
Steps:
Rank the projected misstatement for accounts with BV less than the sampling interval (from
largest to smallest)
Multiply each projected misstatement by the incremental reliability factor, reduced by one
Sum the resulting amounts to get Incremental Allowance
Reliability factor Increment Increment 1 Projected Incremental
misstatement Allowance
2.31 - - - -
3.89 1.58 0.58 1081 627
5.33 1.44 0.44 692 305
6.69 1.36 0.36 346 125
1057

13
 f. Upper limit on misstatement = projected misstatement + Basic precision + Incremental allowance
= 2919 + 19,984 + 1057 = 23,960
2. Draw final conclusion
Decision rule: If the upper limit on misstatement is less than or equal to the tolerable misstatement, we
conclude that the balance is not materially misstated. Since upper limit on misstatement of Br.23,960 is less
than tolerable misstatement of Br. 50,000, we can conclude that account receivable balance is not materially
misstated.

If the upper limit on misstatement were greater than the tolerable misstatement, the auditor may:

Increase the sample size.

Perform other substantive procedures.
Request the client adjust the accounts receivable balance for 26,040 (i.e. 50,000 23,960).
If the client refuses to adjust the account balance, the auditor would consider issuing a qualified or
adverse opinion.

Note
The expansion factor has direct effect on sample size
The smaller the specified risk of incorrect acceptance, the larger the expansion factor
When the sample includes no misstatements, the projected misstatement is equal to zero. Thus, upper limit
on misstatement consists only of basic precision.
For calculating the sample size, the zero misstatement row of the reliability factor table is always used.
Allowance for sampling risk is not provided for book value in excess of sampling interval because the entire
balance is audited
When understatement errors are detected, the auditor can calculate a NET upper limit on misstatement.
Procedures:
Compute projected misstatement for understatements
Subtract project misstatement of understatements from upper limit on overstatements
The result is Net upper limit on misstatement
Use Net upper limit on misstatement for conclusions

EXERCISES

Exercise 1

Abebe, ACCA, was conducting the audit of ABC Company for the year ended December 31, 2010. He plans to
use Monetary unit sampling to audit the clients inventory balance. The balance at December 31, 2010 was Br
9,000,000. Consider the following data:
Tolerable misstatement = 360,000 Birr
Expected misstatement = 90,000
Risk of incorrect acceptance = 5%

Abebe has identified the following misstatements after conducting sampling testing:
Misstatement Number Book value Audited value
1 10,000 7500
2 9,000 6000
3 60,000 0
4 800 640

14
Required:
1. compute the following:
a. the sample size. d. basic precision
b. the sampling interval. e. incremental allowance
c. projected misstatement (error) f. Upper limit on misstatement

2. What conclusion should Abebe make about inventory account?

3. Assume that, in addition to the four misstatements identified above, Abebe has identified the following
two understatement:
Misstatement Number Book value Audited value
5 6,000 6500
6 750 800

Compute the net upper limit on misstatement

Exercise 2

Suppose you are assigned to audit the accounts receivable balance of Alem Company. You decide to use
statistical sampling to test the reasonableness of the recorded book value. Because the company's internal control
procedures over accounts receivable have been evaluated by you as excellent and you believe few errors will be
found, you decide to use probability proportional-to-size sampling. The company has 5,000 customer accounts
with a total book value of Br.1, 700,000. You decide Br.75, 000 is the maximum tolerable misstatement and
anticipate that there may be Br.15, 000 of error in the population.

You wish to limit the risk of incorrect acceptance to 5%. It is your intention to seek positive confirmation of
accounts included in your sample and to apply alternative procedures to accounts for which no reply is received.
Based on your procedures, the following errors were found in the sample:

Sample item 1 2 3 4 5
Book value 400 750 20,000 1000 7000
Audited Value 300 705 16,000 1200 7500

Reliability factors for errors of overstatement (partial)

Number of Risk of incorrect Acceptance
overstatement errors 1% 5% 10%
0 4.61 3.0 2.31
1 6.64 4.75 3.89
2 8.41 6.30 5.33
3 10.05 7.76 6.69
4 11.61 9.61 8.00
5 13.11 10.52 9.28

Expansion Factors (EF) for expected error

Risk of Incorrect Acceptance
1% 5% 10% 15% 20% 25% 30% 37% 50%
EF 1.9 1.6 1.5 1.4 1.3 1.25 1.2 1.15 1.0

Required:
a. Compute the sample size.
b. Compute the sampling interval.
15
c. Compute projected misstatement (error)
d. Compute basic precision
e. Compute incremental allowance
f. Upper limit on misstatement
g. State your conclusion based on the above analysis

Exercise 3
The external auditor of Sheger Corporation has been testing the effectiveness of the design and implementation of
Lagar Corporations (the client) internal control system concerning all purchase invoices (100 invoices) received
from suppliers during the year ended December 31, 2010. From past experience and his professional judgment,
he set the risk of assessing control risk too low (type II error) and tolerable deviation rate to be 5% and 12%
respectively. He selected a sample of 15 purchase invoices and tested for the agreement between purchase invoice
and the related purchase order and receiving reports, and found that 3 purchase invoices were not supported by
purchase orders (deviations from the prescribed control). He does not believe that the sample of 15 purchase
invoices completely represent the population of purchase invoices. As a result, he provided for allowance for
sampling risk of 2%.
Required:
a. Determine sample deviation rate
b. Compute upper deviation rate
c. Should the internal control system over purchases be relied on? If not, why?

16