Audit Sampling

1
This standard helps the auditor in

◦ Using of Statistic and Non-statistics

sampling techniques
◦ Designing and selecting the audit sample
◦ Performing test of controls, test of details
and
◦ Evaluating the results from the sample

2
“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, is called audit sampling.”

“The entire set of data from which a sample is

selected and about which the auditor wishes
to draw conclusions.”

3
A representative sample is one in which the
characteristics in the sample of audit interest
are approximately the same as those of the
population.

It means that Sample items are similar to the

items not sampled.

4
Say, it is a part of client’s internal control to
attach a shipping document to every duplicate
sales invoice by a Clark, the procedure is not
followed exactly 3 percent of the time.
(Assessed after internal control systems).
ØIf the auditor selects a sample of 100 duplicates sales
invoice and finds three missing – The sample is
highly representative
ØIf finds two or four are missing- The sample is
reasonably representative
ØIf no or many missing –The sample is non
representative.

5
Question: How can auditors decide the selected
sample is representative even after all testing
is completed?

=It is very difficult to say the selected sample is

representative even all testing is completed.

Say, Can we conclude that sales revenue is fairly

stated if sample tests do not reveal any
misstatements?

6
But,

Auditor can increase the likelihood of a sample

being representative by using care in
1. Design
2. Selection and
3. Evaluation

7
Reasons to be non-representative

1. Non sampling error i.e Non sampling Risks

and
2. Sampling error i.e Sampling Risks

8
It occurs when audit tests do not uncover
existing exception in the sample. Main
causes of non-sampling risks are-

1. Auditor’s failure to recognize exception, and

2. Inappropriate or ineffective audit procedure

Say, in our previous example if the auditor

concluded that no exception existed , there
is a non sampling error.

9
Ways to control non-sampling risks:

} Careful design of audit procedure

} Proper planning and instructions
} Supervision and control and

} Through review etc.

10
It is inherent part of audit that occurs from
testing less than entire population.

Ways to control sampling risks:

1. By adjusting sample size and

2. By using of appropriate method of sample

selection
This does not eliminate the sampling risks but
helps the auditor to measure the risk
reliably and reduce the sampling risk at
acceptable level.
11
Can be divided into TWO broad categories:

1. Statistical/ Probabilistic and

2. Non statistical / Non Probabilistic

12
Statistical sampling is a sampling method
where the sampling risk can be quantifiable.
Such as 95% confidence level i.e 5%
sampling risk.

It can be said probabilistic sampling. It is a

method of 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.

13
In no statistical sampling, the auditor does not
quantify sampling risk. It is judgmental
process to reach conclusion.

It can be said non probabilistic sampling. It is a

method of selecting a sample in which the
auditor use professional judgment rather
than probabilistic method to select sample
items.

14
Non Probabilistic Sample Probabilistic Sample Selection
Selection Methods Methods

1. Simple Random
Sample Selection
1. Directed Sample
2. Systematic Sample
Selection
Selection
2. Block Sample
3. Probability
Selection
Proportional to Size
3. Haphazard Sample
Sample Selection
Selection
4. Stratified Sample
Selection

15
1. Directed Sample Selection
Ø Based on some judgmental criteria
Ø Every item has no equal chance to select
Ø Deliberately select sample
Ø May be representative or may not

Commonly used criteria include:

i. Items most likely to contain misstatement
ii. Items contain selected population
characteristics and
iii. Large amount coverage etc.

16
2. Block Sample Selection
Ø It is way of selection of several items in
sequence

Say, selection of a sequence of 100 sales

transactions from the sales journal for the
third week of March.
Or a total sample of 100 could also be selected
by taking 5 blocks of 20 items each, 10
blocks of 10 each or 50 blocks of 2 each
etc.

17
3. Haphazard Sample Selection
Ø Here sample is select without any bias.
Ø Here auditor select population item
without regard to their size, source or any
other distinguish criteria.

18
1. Simple random sample selection
Ø Here every possible combination of
elements in the population has an equal
chance of constituting sample.

Auditor can use here-

} Random number tables
} Computer generation of random number

19
2. Systematic Sample selection
Ø Here auditor calculates an interval and
then methodically selects the items for the
sample based on the size of the intervals.
Interval= Population size/ Sample size
Say, Population of sales invoices range from 652 to
3151 and desired sample size is 125, the interval
will be (3151-651)/125=20
Now select any random number between 0 and 19 to
determine the starting point for the sample.
Say, select 9 randomly, then the first item in the
sample is invoice number 661 (652+9).
Remaining 124 items will be 681 (661+20), 701
(681+20), and so on through items 3141.
20
3 & 4. Probability Proportional to size and
Stratified Sample selection
Ø Here the probability of selecting any
population item is proportional to its
recorded amount.
Ø This method is called sampling with
probability proportional to size.

In stratified sampling-
Ø Population is divided in to sub
points by size
Ø Take larger sample from larger
subpopulation
21
Monetary Unit Sampling is a type of value
weighted selection in which sample size,
selection and evaluation results in a
conclusion in monetary amounts.

When performing tests of details it may be

efficient to identify the sampling unit as
the individual monetary units that make up
the population

22
a) Plan the Sample b) Select the Sample and
Performed the audit
procedures
1. State the objectives of the
audit tests 10. Select the sample
2. Decide whether audit 11. Perform the audit tests
sampling applies
3. Define attributes and
exception condition
4. Define the population
5. Define the sample unit
6. Specify the tolerable c) Evaluate the Results
exception limit
7. Specify acceptable risk of 12. Generalize from the sample
assessing control risks too to the population
low
13. Analyze exceptions
8. Estimate the population
14. Decide the acceptability of
exception rate
the population
9. Determine the initial sample
size 23
Summary
of Audit
Sampling
Steps

24
 Factors Effect on
Sample Size

1. An increase in the extent to which the Increase

auditor’s risk assessment takes into account
relevant controls
2. An increase in the tolerable rate of deviation Decrease

3. An increase in the expected rate of deviation Increase

of the population to be tested
4. An increase in the auditor’s desired level of Increase
assurance that the tolerable rate of deviation is
not exceeded by the actual rate of deviation in
the population
5. An increase in the number of sampling units Negligible
in the population effect
25
 Factors Effect on
Sample Size

1. An increase in the auditor’s assessment of Increase

the risk of material misstatement
2. An increase in the use of other substantive Decrease
procedures directed at the same assertion
3. An increase in the auditor’s desired level of Increase
assurance that tolerable misstatement is not
exceeded by actual misstatement in the
population
4. An increase in tolerable misstatement Decrease
5. An increase in the amount of misstatement Increase
the auditor expects to find in the population

26
Thanks

27