Understanding the POPULATION for audit sampling

Population means the entire set of data from which a sample is selected and bout which the auditor
wishes to draw conclusions. In audit, population refers to transactions or records of ALE. Population is
very important because this is where we start gathering for chain of evidence.
When auditing, instead of testing all items in the population, auditor selects a sample from the
population. There are different documents that will be collected but not necessarily form part of the
population. A clearly described audit procedure will have an easily identifiable population.
When sampling, auditor gets a mix from the population to test correctness of transactions or items.
Different sampling methods:
1. Haphazard Sampling –
2. Random Sampling – requires auditor to know how many types of items are in the population
and use statistics to create a random sample
3. Stratification – dividing population into sub-groups / strata and choose samples within the sub-
groups / strata. Note that small transactions can be worth one large transaction. Consider risk
when creating samples or stratifying. Consider also what your are investigating such as when
identifying bad debts, stratify by days overdue.

ISA 530
Audit Sampling
Why do we conduct sampling?
1. To give reasonable assurance
2. Because audits are performed under time pressure
3. Due to large and high-volume transactions

Scope of ISA 530

- Applied when auditor uses audit sampling in performing audit procedure detailing statistical and
non-statistical sampling methods used
- In relation to ISA 500, audit sampling is one of the means for selecting items for testing. This
deals with auditor’s responsibility to design and perform audit procedures to obtain sufficient
appropriate audit evidence to be able to draw reasonable conclusions.
 Objective
- Provide reasonable basis for the auditor to draw conclusion about the population from which
sample is selected.

Definition
- Audit sampling - application of audit procedures to less than 100% of items within a population .
All sampling units have a chance of selection, although chances are not equal chances of
selection since other items may be given priority. When performing analytical procedures, there
is no sampling since auditor is looking at everything.
- Population – entire set of data from which sample is selected and which auditor wishes to draw
conclusion.
- Sampling risk – conclusion based on sample is different if entire population were subjected to
the same audit procedure. May lead to 2 types of erroneous conclusions
I. A wrong conclusion stating that controls are effective or there is no material misstatement.
The auditor is primarily concerned in this type of error because ineffective audit procedure
lead to inappropriate audit opinion. This shows understated level of risk resulting to
insufficient evidence which increases chance of inappropriate audit opinion.
II. A wrong conclusion stating that controls are NOT effective, even though it is effective, or
there is a material misstatement when in fact there is none. This error shows a high audit risk
that needs to be lessen. This affect audit efficiency because result to additional audit work.
There is no increase risk. Decreases profit margin because too much audit risk increases audit
effort.
- Non-sampling risk – risk that auditor reaches an erroneous conclusion for any reason not related
to sampling risk such risk is tried to be controlled by creating an effective process but some of
these risk are also out of control. Involves human error or fraud.
- Anomaly = misstatement or deviation that is demonstrably not representative of misstatement
or deviations in a population. These are irregularities not expected to be seen.
- Sampling unit = means the individual items constituting a population.
- Statistical sampling = approach to sampling that has the ff characteristics:
i. Random selection of the sample items
ii. The use of probability theory to evaluate sample results, including measurements of
sampling risk
In the absence of the said characteristics such sampling approach is called non-statistical
sampling
- Stratification = process of dividing population into sub-population with similar characteristics
often in monetary value
- Tolerable misstatement = monetary amount set by auditor where auditor seeks to obtain an
appropriate level of assurance that actual misstatement does not exceed the monetary amount
set. Materiality level for a specific account based on the main level of materiality adjusted for
risk related to specific account or process. Used when doing substantive testing.
- Tolerable rate of deviation = used when testing internal control. A percentage rate of control
failure. An acceptable percentage or rate of deviation from prescribed internal control. Increase
in control risk assessment resulting to decrease in detection risk

Requirements
A. Sample Design, Size and Selection of Items for Testing
 - In designing an audit sample, consider purpose of audit procedure and characteristics of
population from which sample is drawn. Know what you are testing, design a procedure to suit
and then select an appropriate sampling method.
- Determine sample size sufficient to reduce sampling risk to an acceptable low level by using
statistical and non-statistical methods. Commonly used by firms is non-statistical method.
- Select items for the sample in such a way that each sampling unit in the population has a chance
of selection. Such chance is not necessarily equal because some are given priorities.

B. Performing Audit Procedure

- Perform audit procedures appropriate to the purpose and item selected
- If procedure is not applicable to the selected item, perform procedure on a replacement item.
- If auditor cannot apply the designated audit procedure or suitable alternative procedure, to the
selected item, treat such item as a deviation from the prescribed control. Consider limitation of
scope

C. Nature and Cause of Deviations and Misstatement

- Investigate the nature and cause of any deviation or misstatement identified and evaluate
possible effect on purpose of audit procedure and on other areas of the audit. Determine if the
deviation or misstatement is a one-off issue or a recurring issue. This may lead to selecting
another sample or perform analytical procedure or talk to management.
- If misstatement or deviation is considered as an anomaly, obtain higher degree of certainty that
such misstatement or deviation is not representative of the population. Also obtain higher
degree of certainty by performing additional audit procedures to obtain sufficient appropriate
audit evidence that such misstatement or deviation does not affect remainder of the population.

Projecting Misstatements
- Project misstatement found in the sample to the population. Is equal to errors from the sample
and divide by value of the sample and multiply to the value of the population. Afterwards,
compare to tolerable misstatement for such particular account. If projected misstatement >
tolerable misstatement, needs adjustments. If projected misstatement < tolerable
misstatement, it is immaterial.

Appendix 2 Example of factors influencing sample size for the test of controls
Appendix 3 Example of factors influencing sample size for tests of details
Appendix 4 Sample Selection Methods
A. Random Selection – applies random sampling number generators
B. Systematic Selection – number of sampling units in a population is divided by the sample size to
give a sampling interval Although the starting point may be determined haphazardly, the sample
is more likely to be truly random if it is determined by use of a computerized random number
generator or random number tables. When using systematic selection, the auditor would need
to determine that sampling units within the population are not structured in such a way that the
sampling interval corresponds with a particular pattern in the population.
C. Monetary Unit Sampling - type of value-weighted selection (as described in in which sample
size, selection and evaluation results in a conclusion in monetary amounts.
D. Haphazard Sampling - selects the sample without following a structured technique. Although no
structured technique is used, the auditor would nonetheless avoid any conscious bias or
predictability and thus attempt to ensure that all items in the population have a chance of
selection. Haphazard selection is not appropriate when using statistical sampling. Most
commonly used by auditors.
E. Block Selection - selection of a block(s) of contiguous items from within the population. Block
selection cannot ordinarily be used in audit sampling because most populations are structured.
rarely be an appropriate sample selection technique when the auditor intends to draw valid
inferences about the entire population based on the sample.