2/26/2021

Prepared by:
Alex Almodiel, CPA, MBA

What is audit sampling?

The application of audit procedures to
less than 100% of items within a
population of audit relevance such that
all sampling units have a chance of
selection in order to provide the auditor
with a reasonable basis on which to
draw conclusions about the entire
population.

1
 2/26/2021

Sampling Risk
The risk that the auditor’s conclusion based on
a sample may be different from the conclusion
if the entire population were subjected to the
same audit procedure.

Non-Sampling Risk
The risk that the auditor reaches an
erroneous conclusion for any reason not
related to sampling risk.

 Sample the wrong population to test an

assertion.
 Failure to detect a misstatement when
applying an audit procedure.
 Misinterpreting an audit result.

2
 2/26/2021

Audit Sampling
Types of Sampling Risk

Types of Sampling Risk

 Risk of Incorrect Rejection (Type I)
 Risk of Incorrect Acceptance (Type II)

3
 2/26/2021

Risk of Incorrect Rejection

 Deciding that the population tested is not
accepted when in reality it is.
 Relates to the efficiency of audit.
 More audit work in order to reach correct
conclusion.

Risk of Incorrect Rejection:

Test of Controls & Substantive Tests
A. Test of Controls
 The risk that the sample supports a conclusion
that the control is not operating effectively
when, in truth, it is operating effectively.
 Level of reliance - risk of under-reliance or risk
of assessing control risk is too high.

B. Substantive Testing
 The risk that the sample supports the conclusion
that the recorded balance is materially
misstated when it is NOT materially misstated.

4
 2/26/2021

Risk of Incorrect Acceptance

 Deciding that the population tested is
accepted when in reality it is not.
 Relates to effectiveness of audit.
 Can result to failure to detect material
misstatements.
 Due to potential result of failure to
detect material misstatements, auditors
design their sampling application to keep
this risk to an acceptably low level.

Risk of Incorrect Acceptance:

Test of Controls & Substantive Tests
A. Test of Controls
 The risk that the sample supports a conclusion
that the controls are operating effectively
when, in truth, it is not operating effectively.
 Level of reliance - risk of over-reliance or risk
of assessing control risk is too low.

B. Substantive Testing
 The risk that the sample supports the
conclusion that the recorded account balance
is not materially misstated when it is actually
materially misstated.

5
 2/26/2021

Audit Sampling
Types of Audit Sampling

Types of Audit Sampling

Non-statistical
Statistical Sampling
Sampling

6
 2/26/2021

Non-statistical Sampling
 Also called judgmental sampling (not using
statistical techniques)
 Not using statistical techniques to determine
the sample size, select the sample, and/or
measure sampling risk when evaluating the
results.
 Simpler to use and more consistently
applied than statistical sampling.

Statistical Sampling
 Allows auditor to quantify and control
sampling risk.
 Uses statistical techniques and the law of
probability to compute sample size and
evaluate the sample results, thereby
permitting the auditor to use the most
efficient sample size and to quantify the
sampling risk for the purpose of reaching
statistical conclusion about the population.

7
 2/26/2021

Audit Sampling
Important Factors in Audit Sampling

Important Factors in Audit Sampling

A. Confidence Level
 Desired level of assurance in the results.
 The higher the confidence level the auditor
desires, the larger the sample size.
B. Tolerable Error
 Acceptable deviation rate or misstatements.
 The lower the tolerable error, the larger the
sample size.
C. Expected Error
 Historical deviation rate or misstatements.

8
 2/26/2021

Audit Sampling
Relationship between evidence types and audit
sampling, Testing all items with a particular
characteristic, and testing only one or few items

Types of Evidence and Audit Sampling

Audit
Type of Evidence
Sampling
Inspection of tangible assets Yes
Inspection of records & documents Yes
Re-performance Yes
Recalculation Yes
Confirmation Yes
Analytical Procedures No
Scanning No
Inquiry No
Observation No

9
 2/26/2021

Testing All Items with a Particular

Characteristic
 Accounts or class of transactions is made up of a few large items, the
auditor may examine all the items in the account or class of transactions.
Because the entire class or balance is subjected to a percent examination,
such an audit procedure does not involve sampling.
 When auditor tests all items with a particular characteristic of interest
based on risk or monetary value, it does not involve sampling anymore.
 For example, certain transactions that look unusual or present greater
risk.
Another example, a relatively small number of large transactions make up
a relative large percentage of an account or class of transactions, auditor
will typically test all the transactions greater than a particular currency
amount.

Testing Only One or Few Items

Usually used when automated information systems are used to
process transactions.
 Auditor tests the automated IT controls by testing one or a few of
each type of transactions at a point in time.
 Auditor tests general controls over system and program changes to
provide evidence that the automated controls have been operating
over the audit period. This type of test of automated controls does
not involve audit sampling.

10
 2/26/2021

Audit Sampling
Types of Statistical Sampling Techniques

Statistical Sampling Techniques

 Attribute Sampling
 Monetary-Unit Sampling
 Classical Variables Sampling

11
 2/26/2021

Attribute Sampling
 Use to estimate the proportion of a
population that possesses a specified
characteristic.
 Often used to test whether a company's
internal controls are being followed.

Monetary-Unit Sampling
 A type of value-weighted selection in
which sample size, selection and
evaluation results in a conclusion in
monetary amounts.
 E.g. Examining accounts receivable –
select accounts with large amounts.

12
 2/26/2021

Classical Variables Sampling

 Treat each individual item in the
population as a sampling unit.
 This method is most like the statistics
classes you had to take in high school and
college.
 Mean-per-unit
 Ratio estimation
 Difference

Classical Variables Sampling:

Mean-per-Unit
For instance, if you add 10 + 30 + 50 to get 90, and then divide 90 by 3 (the number
of values in this example), you get 30, which is the mean. As an auditor, you apply
this statistical concept to evaluate characteristics of your total population. Taking
the average value (mean) of items in your sample, you can estimate the true
population value.

For example, you have a total population of 3,000 items in accounts receivable, and
your sample size is 50. Adding up the individual values of the 50 items, you get a
total of P2,000; therefore, your mean is P40 (2,000/50). Your mean estimate of the
true value of accounts receivable is P120,000 (P40 x 3,000).

Considering this data with your sampling risk, confidence level, and error rate, if
your confidence level is 95 percent and your error rate is 10 percent, you can say
that you’re 95 percent confident that the total value of accounts receivable is
P120,000, plus or minus P12,000 (P120,000 times your error rate of 10 percent).

13
 2/26/2021

Classical Variables Sampling:

Ratio Estimation
If your sample for any of your client’s accounts shows errors of P1,000
in a total sample of P10,000, your misstatement ratio is 10 percent
(P1,000/P10,000).

You would then apply this ratio to the entire population. If the entire
population totals P50,000, your projected misstatement, which is an
estimation of the misstatement in the entire population, is P5,000
(P50,000 x 10 percent).

Classical Variables Sampling:

Difference
For example, your population consists of 5,000 items and your sample
consists of 1,000 items. Your audit procedures find errors totaling P500.
The projected misstatement is P2,500 [(P500/1000) x 5,000 items].

14
 2/26/2021

Audit Sampling
Attribute Sampling Applied as Test of Controls

Attribute Sampling as Test of Control:

Step by Step Process
1. Determine the test objectives.
2. Define the population characteristics.
3. Determine the sample size.
4. Select sample items.
5. Perform audit procedures.
6. Calculate the sample deviation rate and upper limit deviation rates.
7. Draw final conclusions.

15
 2/26/2021

Step 1:
Define the test objectives.
 State the objectives of test of control.
 Each objective needs to be related to an assertion of class of
transaction or account balance.

Control Objective

To ensure that recorded sales in the system are all approved

(existence or occurrence).

Step 2:
Define the population characteristics.
 Define the sampling population.
 Define the sampling unit.
 Define control deviation.

Sampling Population Sampling Unit Control Deviation

Recorded sales from months Any sales invoice without

of January to March and Sales invoice packets supporting shipping documents
October to December of or with supporting shipping
fiscal year 2018. documents but no approval
signature.

16
 2/26/2021

Step 3:
Determine the sample size.
 Determine the desired confidence level.
 Determine the tolerable deviation rate.
 Determine the expected population deviation rate.
Confidence Level Tolerable Deviation Rate Expected Population
95% 5% Deviation Rate
(reliance on internal (maximum tolerance of departure 2%
control) from internal control) (maximum tolerance of departure
Low tolerable deviation rate from internal control)
High confidence means larger sample size. Low expected population
level means larger deviation rate means small
sample size. SAMPLE SIZE: 181 sample size.
Refer to statistical table

17
 2/26/2021

Suggested Tolerable Deviation Rates for

Assessed Level of Control Risks

Planned Assessed Level of Tolerable

Control Risk Deviation Rate
Low 3% to 5%
Moderate 6% to 10%
Slightly before maximum 11% to 20%
Maximum Omit Test of Control

Step 4:
Select sample items.
 As required by auditing standards, sample items be selected in such
a way that the sample can be expected to represent the population.
 Selection methods can be:
 Random-number selection
 Using random number generators by spreadsheet allocation or audit
sampling software.

 Systematic selection
 The number of sampling units in the population is divided by the sample
size to give a sampling interval, for example 50, and having determined a
starting point within the first 50, each 50th sampling unit thereafter is
selected.

18
 2/26/2021

Step 5:
Perform audit procedures.
 Conduct the audit procedure to meet the test objective. Auditor might
encounter the following:
 Voided documents
 Unused or inapplicable documents.
 Inability to examine sample item.
 Stopping the test before completion.
Understand and analyze the deviations observe (nature, cause and consequence
of the deviation).

Audit Procedures
1. For each sales invoice packet, note the shipping document number referenced on the
sales invoice document.
2. Verify if the shipping document attached to it has the same reference number.
3. Verify that the “Approved by” section of the shipping document has valid signature.

Step 6:
Calculate the sample deviation rate and upper limit
deviation rates.
 Summarize the deviation for each control tested and evaluate the results.
 Compute the sample deviation rate from the samples tested.
 Determine the computed upper limit deviation rate.

Result of Audit Procedures

Out of 181 sales invoice packets tested, two (2) were noted with exceptions. That is
1% sample deviation rate. Per statistical table, the allowance for sampling risk of
sample size 181 with 2 exceptions found is 4.2%. The computed upper deviation
rate is 5.2% (1% + 4.2%).

19
 2/26/2021

Step 7:
Draw final conclusions.
 Compare the tolerable deviation rate (TDR) to the computed upper
deviation rate (CUDR).
 If TDR > CUDR, internal control is operating effectively.
 If TDR < CUDR, internal control is not operating effectively.
 Control deficiency – verify if there are any compensating controls.
 Test other control procedures to support planned level of control risk or increased
planned level of control risk and modify the nature, timing, and extent substantive
procedures.
Conclusion

Tolerable deviation rate is 5% and computed upper deviation rate is 5.2%. Therefore, the
appropriate internal control for the approval of recorded sales transaction is not operating
effectively. Auditor shall increase the assessed level of control risk for authorization of
recorded sales and substantive procedures related to existence or occurrence.

20
 2/26/2021

Sample size
No. of deviations

Audit Sampling
Non-Statistical Sampling for Test of Controls

21
 2/26/2021

Non-Statistical Sampling for Test of Controls:

Step by Step Process
1. Determine the test objectives.
2. Define the population characteristics.
3. Determine the sample size.
4. Select sample items.
5. Perform audit procedures.
6. Calculate the sample deviation rate and upper limit deviation
rates.
7. Draw final conclusions.

Non-Statistical Sampling Test of Control:

Determine the sample size.
 Auditor is not required to use statistical formula or table to
determine sample size.
 Instead, guidance in audit firm policy and professional judgment are
used to relate these factors and determine the appropriate sample
size for the application.

22
 2/26/2021

Example of Firm’s
Non-Statistical Sampling Guidelines

Desired Level of Control Reliance Sample Size

Low 15 to 20
Medium 25 to 35
High 40 to 60

Non-Statistical Sampling Test of Control:

Select sample items.
 Allows the use of random-sample or systematic-sample.
 Allows also other sample selection methods such as:
 Haphazard Selection
 Auditor selects the sample without following a structured technique.
 Sampling units are selected without any conscious bias or predictability.
 Not appropriate when using statistical sampling.

 Block Selection
 Involves selection of a block(s) of contiguous items from within the population.
 Cannot ordinarily be used in audit sampling because most populations are structured
such that items in a sequence can be expected to have similar characteristics to each
other, but different characteristics from items elsewhere in the population.

23
 2/26/2021

Non-Statistical Sampling Test of Control:

Calculate the sample deviation rate and computed
upper deviation rates.
 Auditor can calculate the sample deviation rate but cannot quantify
the computed upper deviation rate and the sampling risk associated
with the test.
Sample deviation rate should not exceed expected population
deviation rate. Otherwise, consider assessing control risk as high.

Audit Sampling
Monetary Unit Sampling:
Substantive Test of Class of Transaction or
Account Balance

24
 2/26/2021

Attribute Sampling as Test of Control:

Step by Step Process
1. Determine the test objectives.
2. Define the population characteristics.
3. Determine the sample size.
4. Select sample items.
5. Perform audit procedures.
6. Calculate the projected misstatement and upper limit on
misstatement.
7. Draw final conclusions.

Step 1:
Define the test objectives.
 State the objectives of substantive test.
 Each objective needs to be related to an assertion of class of
transaction or account balance.
Account Balance Objectives

To ensure that accounts receivable presented on the financial

statements as of 12/31/2018 represent valid claims of the company
and valued accordingly (rights and accuracy assertions).

25
 2/26/2021

Step 2:
Define the population characteristics.
 Define the sampling population.
 Define the sampling unit.
 Define misstatement

Sampling Population Sampling Unit Misstatement

Accounts receivable of Customer balances as of Any difference between the
P2,500,000.00 as of 12/31/2018 composing the customer balance per AR
12/31/2018 presented on Accounts Receivable of Subsidiary Ledger in support of
the 2018 financial P2,500.00.00 as of 12/31/2018 the AR as of 12/31/2018
statements. presented on the 2018 financial presented on the financial
statements. statement and AR confirmation
letters.

Step 3:
Determine the sample size.
 Determine the desired confidence level or acceptable risk of incorrect acceptance.
 Determine the tolerable misstatements.
 Determine the expected misstatements.

Confidence Level Tolerable Misstatement Expected Misstatement

95% 5% (P125,000.00) 1% (P25,000.00)
High confidence Low tolerable misstatement Low expected misstatement
level means more means more audit work and larger deviation rate means less audit
audit work and sample size. work and small sample size.
larger sample size.
SAMPLE SIZE: 93
Refer to statistical table

26
 2/26/2021

Step 4:
Select sample items.
 As required by auditing standards, sample items be selected in such
a way that the sample can be expected to represent the population.
 Use systematic selection as sampling method (e.g. probability-
proportionate-to-size selection – which uses interval to select sample
items).
 Book value of account (P2,500,000.00) divided by sampling size (93
items) equals P26,882 sampling interval.

27
 2/26/2021

Step 5:
Perform audit procedures.
 Conduct the audit procedure to meet the test objective.
 If evidence (or any other available evidence) is not available, such
item shall be considered misstatement.
Audit Procedures
1. After obtaining list of customer balances as of 12/31/2018 from client, request from
client to fill out the confirmation letter template for each selected sample of
customers.
2. Obtain from client the filled out confirmation letters.
3. Mail the confirmation letters to customers.
4. Tabulate customer responses.
5. Follow up responses to customers who have not yet sent responses via e-mail or
phone call.
6. Document the result of confirmation.

Step 6:
Calculate the projected misstatement and upper
limit on misstatement.
Compute the projected misstatement from the samples tested.
 Determine the upper limit on misstatement.
 Summarize the results.

Book value = P2,500,000.00

Tolerable misstatement = P125,000.00
Sample size = 93
Desired confidence level (risk of incorrect acceptance) = 5%
Expected amount of misstatement = P25,000.00
Sampling interval = P26,882.00

28
2/26/2021

29
 2/26/2021

Step 7:
Draw final conclusions.
 Compare the tolerable misstatement (TM) to the computed upper
limit on misstatement (CULM).
 If TM > CULM, account is not materially misstated.
 If TM < CULM, account is materially misstated.

Conclusion

Tolerable misstatement is P125,000.00 and the upper limit on misstatement is

P150,621.00. Therefore, the accounts receivable is materially misstated.

30
 2/26/2021

References
Primary Reference
• Philippine Standards on Auditing
• Auditing & Assurance Services 4th Edition by Messier/Glover/Prawitt

Web Sites
• https://www.dummies.com/business/accounting/auditing/how-does-
classical-variables-sampling-work/
• www.Investopedia.com
• https://www.youtube.com/watch?v=VQzHqO7nlXw
• https://www.youtube.com/watch?v=hKxX8-Uu61E

31