Explain the concept of

representative sampling: sampling

and non sampling risk

15-1
 REPRESENTATIVE SAMPLING
Why do we sample?
Draw a general conclusion about the population
Save money and time
Where do we use sampling? 2 areas
1. Test of control Attribute (characteristic) sample: Tolerable
error rate 1/5 or 20%
2. Substantive testing: variable testing: $ do we accept or reject
an account balance
Audit Risk = IH x CR x Detection risk

15-2
REPRESENTATIVE SAMPLING
A representative sample (assume. Why?) is one in which the
characteristics in the sample are approximately the same as those
of the population. Sample items are similar to the population.
• Auditors strive to get a representative sample for testing.
• Auditors never know if a sample is representative or not, but the auditor can
increase the likelihood by using care in designing the sampling process,
sample selection, and evaluation of sample results.
A sample, even a representative sample, has the risk of two types of errors: a
sampling error and a nonsampling error.
• The risks of these two types of errors are called sampling risk and
nonsampling risk.

3
 REPRESENTATIVE SAMPLING (CONT.)

Sampling risk is the risk that an auditor reaches an incorrect conclusion

because the sample is not representative of the population. Example
Sampling risk can be controlled by the auditor by:
1. Adjusting sampling size. President’s approval rating.
2. Using an appropriate method of selecting sample items from the population.

Nonsampling risk is the risk that the auditor reaches an incorrect

conclusion for any reason not related to sampling risk. Common reasons are:
• Auditor’s failure to recognize exceptions
• Ineffective audit procedures

15-4
 EXAMPLE: ATTRIBUTE SAMPLE I/C. TYPE 1
ALPHA ERROR
Population: 1,000 Invoice
Sample: 100
Tolerable error rate: 6%. Greatest error I am willing to tolerate before I don’t rely
Actual population error: 30. Given
30/1,000 = 3%
Of the sample size, I found 20 errors. Now what?
Under-rely on I/C  RMM high  Detection risk Low  I do more work
Type of I or Alpha error: efficiency
Same applies to substantive dollar testing. You reject the balance

5
EXAMPLE: ATTRIBUTE SAMPLE I/C. TYPE 2 OR
BETA ERROR
Population: 1,000 Invoice
Sample: 100
Tolerable error rate: 7%. Greatest error I am willing to tolerate before I don’t rely
Actual population error: 300
300/1,000 = 30%
Of the sample size I found 5 errors. Now what?
Over-rely on I/C  RMM low  Detection risk high  less work. Miss the misstatement
Type of II or Beta Error: effectiveness.
Same applies to substantive dollar testing. You accept the balance

6
 Sample: Statistical Vs Non Statistical
Selection: Probabilistic and non probabilistic

15-7
STATISTICAL VERSUS NONSTATISTICAL SAMPLING
AND PROBABILISTIC SAMPLE SELECTION
Statistical Versus Nonstatistical Sampling - Both methods GAAS
involve the same three phases when used in audits:
1. Plan the sample
2. Select the sample and perform the tests
3. Evaluate the results
Statistical sampling applies mathematical rules so that the auditor can
quantify sampling risk in planning the sample (step 1) and evaluating
results (step 3).
Nonstatistical sampling does not quantify sampling risk, but a properly
designed nonstatistical sample can provide effective results in audits.

15-8
 STATISTICAL VERSUS NONSTATISTICAL SAMPLING
AND PROBABILISTIC SAMPLE SELECTION(CONT.)

Probabilistic Versus Nonprobabilistic Sample Selection

Probabilistic sample selection – the auditor randomly selects items such that
each item has a known probability of being included in the sample.
• When statistical sampling is used, a probabilistic sample must be used.

Nonprobabilistic sample selection – any other method of selecting a sample.

15-9
 SAMPLE SELECTION METHODS

Probabilistic sample selection methods:

1. Simple random sample selection
2. Systematic sample selection
3. Probability proportional to size sample selection
Nonprobabilistic sample selection methods:
4. Haphazard sample selection
5. Block sample selection

15-10
 SAMPLE SELECTION METHODS (CONT.)
Probabilistic Sample Selection Methods:
• Simple Random Sample Selection – In this selection method, every possible
combination of population items has an equal chance of being included in
the sample.
This requires a method to make sure that all items in the population have an equal
chance of selection.
Auditors often generate random numbers by using one of three computer sample
selection techniques (example on next slide):
Electronic spreadsheets, Random number generators, Generalized audit software.
• With and without replacement: With replacement means the item can be
included in the sample more than once. Not normally used.

15-11
 SAMPLE SELECTION METHODS (CONT.)
Probabilistic Sample Selection Methods (cont.):
• Systematic Sample Selection
• The auditor calculates an interval and then selects items for the sample based on the size of the
interval.
• The interval is determined by dividing the population by the desired sample size.
• Assume: sales invoices ranging from 650 to 3002.
• Desired sample (n) = 120
• Find the interval:
• (3002 – 650)/120 = 19.6.
• Find a random number between 0 and 19. Let’s assume the number is 10.
• First item selected 660 (650 + 10) the 670, then 680, then 690 etc.
• Disadvantage: pattern in the population!

15-12
Probability Proportional to Size and Stratified Sample Selection
In many auditing situations, it is advantageous to select samples that
emphasize population items with larger recorded amounts.
To be covered late.

13
 SAMPLE SELECTION METHODS (CONT.)

Nonprobabilistic Sample Selection Methods:

• Haphazard Sample Selection
• the selection of items without any conscious bias by the auditor
• shortcoming is the difficulty of remaining completely unbiased
• Block Sample Selection
• the auditor selects the first item in a block and then the remainder of the block is
chosen in sequence
• acceptable to use block sampling if a reasonable number of blocks is used

Although these methods seem less logical than probabilistic methods, there are
auditing situations in which a probabilistic method is not practical, such as in the
situation of auditing a population that is not numbered in any way.

15-14
Use nonstatistical sampling in tests
of controls and substantive tests
of transactions.

15-15
 SAMPLING FOR EXCEPTION RATES
When testing controls and performing substantive tests of transactions, the
auditor determines whether the controls are operating effectively and whether
the rate of monetary errors is below tolerable limits.
To test this, auditors estimate the percent of items in a population containing a
characteristic or attribute of interest. This percentage is called the occurrence rate or
exception rate.
Auditors are interested in the following types of exceptions in accounting data:
1. Deviations from the client’s established controls
2. Monetary misstatements in populations of transaction data
3. Monetary misstatements in populations of account balance details

When testing controls and performing substantive tests of transactions, the auditor
focuses on the upper limit of the estimated population exception rate, which is the
computed upper exception rate (CUER).
15-16
15-17