Professional Documents
Culture Documents
BASIC CONCEPTS IN
AUDIT SAMPLING
QUESTION 1
What are the different means in selecting items for testing to gather audit evidence?
ANSWER 1
When designing audit procedures, the auditor may choose either or a combination of
the following means of selecting items for testing:
QUESTION 2
ANSWER 2
100% examination is often used for substantive procedures as opposed for tests
controls
QUESTION 3
When will the auditor resort to selecting specific items only for testing?
ANSWER 3
An auditor will often select specific items for examinations with regards to:
QUESTION 4
ANSWER 4
As defined in PSA 530 (Redrafted), “Audit Sampling”, audit sampling involves the
application of audit procedures to less than 100% of the 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. Simply stated, sampling is a process of selecting a subset of a
population of items for the purpose of making inferences to the whole population.
Accounting populations usually consist of a large number of items, often totalling
millions of peso, and a detailed or 100% examination of all accounts is almost
impossible.
Audit sampling can be used in tests of controls and substantive procedures. In relation
to substantive procedures, sampling can only be used in performing substantive tests
of details because substantive analytical procedures should be applied to a complete
set of data or information so that the relationships generated by computing ratios and
trend analysis are realistic.
QUESTION 5
ANSWER 5
Statistical sampling
Nonstatistical sampling is a selection process where the auditor decides which items
are to be audited. It involves a subjective selection of items for testing and a subjective
evaluation of the results. This approach relies on intuition and non-quantitative
methods in the evaluation process. The reliability of the sample results obtained using
judgemental sampling cannot be estimated because the probability of selection of the
individual items in the population cannot be ascertained.
QUESTION 6
Which of the two approaches in sampling provides more useful audit evidence?
ANSWER 6
Auditors disagree on which sampling method is better. When used properly, both
statistical and nonstatistical sampling approaches may provide sufficient appropriate
audit evidence. Both approaches involve judgement in planning, executing the
sampling plan, and evaluating sample results. Also, both require that appropriate
sampling methods be utilized to provide reasonable assurance that the samples
selected are representative of the population.
Those in favor of statistical sampling maintain that such approach would carry greater
evidential weight in a court of law and that conclusions drawn from statistical sampling
are more defensible in court because the risk of error in the population is objectively
and quantifiably determined.
On the other hand, auditors in favor of the nonstatistical sampling approach believe
that the use of professional judgment is a better defense than a statistical measure of
risk. It may be better to have an expert witness explain how important professional
judgment is in an audit than let a statistician explain that there is a known chance (e.g.,
20% or 50%) that the auditor‟s conclusion was incorrect.
QUESTION 7
ANSWER 7
In obtaining audit evidence, the auditor should use professional judgment in assessing
audit risk and in designing audit procedures to ensure that such risk is reduced to an
acceptably low level. Audit risk is the risk that the auditor may unknowingly fail to
appropriately modify his opinion on financial statements that are materially misstated.
It can be expressed as:
AUDIT RISK = IR x CR x DR
Or
For sampling purposes, audit risk can be affected by sampling and nonsampling risks.
QUESTION 8
ANSWER 8
Nonsampling risk arises from factors that cause the auditor to reach an erroneous
conclusion for any reason not related to the size of the sample, such as:
Nonsampling risk result from human error. It exists regardless of the number of items
selected from a population for testing. Since nonsampling risk is a risk that is
attributable to the auditor, it can never be eliminated but can only be appropriately
reduced through proper engagement planning, supervision and review of the audit
report.
QUESTION 9
ANSWER 9
Sampling risk is the probability that a properly drawn sample may not be
representative of the population; that is, the auditor‟s conclusion based on the sample
may be different from the conclusion reached if the entire population were subjected to
the same audit procedure. Sampling risk exists because the sample chosen may not
be representative of the true population characteristic.
Sampling risk can be reduced by increasing sample size, and it can be eliminated if the
auditor chooses to examine all items in the population.
QUESTION 10
ANSWER 10
QUESTION 11
ANSWER 11
a. Risk of assessing control risk too high. It refers to the risk that sample does not
support the auditor‟s planed degree of reliance of the control when the true compliance
rate supports such reliance. In other words, the risk of assessing control risk too high is
the risk that the assessed level of control risk based on the sample is greater than the
true operating effectiveness of the control structure policy or procedure.
This type of risk pertains to audit efficiency and is likely to result in greater audit effort.
The auditor‟s over-assessment of control risk may result to an unnecessary increase
or extension of substantive procedure. For instance, when an auditor concludes that
control risk is high, he ordinarily sets a lower acceptable level of detection risk and
expands the scope of his substantive procedures in order to compensate for the
perceived control deficiency or weakness. Such additional effort is unwarranted and
would only result to inefficiencies in the audit because more substantive procedures
will be performed than necessary.
The risk of assessing control risk too high is also termed a type 1 error, alpha risk, or
the risk of under-reliance.
b. Risk of assessing control risk too low. It refers to the risk that sample support the
auditor‟s planned degree of reliance on the control when the true compliance rate does
not justify such reliance. Simply stated, the risk of assessing control risk too low is the
risk that the assessed level of control risk based on the sample is less than the true
operating effectiveness of internal control.
This type of risk relates to audit effectiveness and could lead to audit failure. The
auditor‟s under-assessment of control risk may result to reduced scope of substantive
procedures. For instance, if an auditor erroneously concludes that the controls are
effective, control risk would be assessed at a low level and the auditor will
subsequently reduce or restrict the extent and scope of his substantive procedures.
Thus, the substantive procedures may not be effective or enough in detecting material
misstatements that otherwise may exist in the population.
The risk of assessing control risk too low is also referred to as type 2 error, beta risk, or
the risk of over-reliance.
The risk of assessing control too low is more important to auditors tan the risk of
assessing control risk to high.
QUESTION 12
ANSWER 12
a. Risk of incorrect rejection. It refers to the risk that the sample supports the
conclusion that the recorded account balance is materially misstated when in fact, it is
not materially misstated.
The type of risk relates to the audit efficiency. Because of the risk involved in
sampling, an audit might select a sample containing disproportionately more misstates
than the population contains. However, audit client would likely maintain that the
balance is properly stated. The auditor would then perform additional procedures and
gather additional evidence to confirm or dispel previous findings; thus, resulting to
additional effort and extra expanding.
The risk of incorrect rejection is also called type 1 error or alpha risk. This risk is similar
to the risk of assessing control risk too high for test of control.
b. Risk of incorrect acceptance. It refers to the risk that the sample supports the
conclusion that the recorded account balance is not materially misstated when in fact,
it is materially misstated.
This type of risk relates to audit effectiveness. Owing to sampling risk, an auditor
might select a sample containing disproportionately less misstatements than what the
population contains. If the auditor incorrectly accepts a materially misstated account
balance as fairly stated, this would cause the auditor to express an unmodified opinion
on financial statements which actually departs from PFRSs. Ultimately, audit
ineffectiveness results to audit failure.
The risk of incorrect acceptance is also called type2 error or beta risk. This risk is
similar to the risk of assessing control risk too low for test of control.
The risk or incorrect acceptance is far more consequential o the auditor than the risk f
incorrect rejection.
QUESTION 13
The confidence (reliability) level is the complete of sampling risk. Hence, for the test
of control, if the risk of assessing control risk too low is 10%, the auditor‟s confidence
level would be 90% (100%-10%). For a substantive procedure, if the risk of incorrect
acceptance is 15%, the auditor‟s confidence level would be 85% (100%-15%).
QUESTION 14
ANSWER 14
Population refers to the entire set of data from which a sample is selected and about
which the auditor wishes to draw conclusion. A sampling unit. On the other hand, is
defined as the individual items constituting a population.
QUESTION 15
ANSWER 15
The auditor should select items for the sample with the expectation that all sampling
units in the population have a chance of select. The auditor may use the following
sample selection methods:
a. Random sampling
b. Systematic sampling
c. Stratified sampling
d. Haphazard sampling
e. Block sampling
QUESTION 16
Radom or probability sampling involves selecting items from the population so that
each items has an equal or know chance of being selected. Random selection requires
the use of random number tables or random number generators. A random number
table is composed of a list of randomly selected number which may be used by auditor.
Random number generators are computer programs that generate random numbers.
The auditor should make sure that the sample bang selected is representative of the
population from which it is drawn. Random sampling typically involves the following
steps:
Random sampling can be used for both statistical and nonstatistical sampling
approaches.
QUESTION 17
ANSWER 17
Systematic or interval sampling consists of sequencing all items all items or the
population. Sampling units are put in numerical order. The auditor divides the
population into n intervals of equal sizes based on the number of sampling units that
must be chosen for the sample (n). He then chooses sampling unit from each of the
derived intervals. The selection interval can be determined by dividing the population
size (N) by the required sample size (n).
For instance, if the population is composed of 1,000 units and the desired sample size
is 100 units, the auditor select a random starting points between one and the sampling
interval of 10 (1,000/100), He then randomly chooses the first sampling unit from the
first interval. After including the random start unit (e.g.4) as part of the sample, he
auditor then sequentially select every 10 th item of the population (e.g., 14th, 24th,
34th,….).This approach usually result in a true random sample.
However, bias my result if a pattern in the population exist that coincides with the
selection interval. For instance, if every 10th sampling units or multiple of 10 happens to
be a departmental manager, then based on the random start, the sample derived may
yield either all departmental manager or none. Nonetheless, the possibility of
introducing the bias into the sample as a result of a pattern in the population can be
minimized by having multiple starting points in the selection process or by using an
interval that does not coincide with the said pattern.
When there is no numerical sequence to a population, the auditor will find it easier to
use a systematic sampling rather than random sampling. If documents, records, or
transaction are unnumbered, there is no need with systematic sampling to number
them physically. If random number table selection was involved, the drawback would
be to require numbering. With systematic sampling, the auditor uses the sampling
interval as the basis for selecting the documents to examine.
Systematic sampling can be used for both statistical and nonstatistical sampling
approaches.
QUESTION 18
ANSWER 18
QUESTION 19
ANSWER 19
Haphazard sampling involves selecting items from the population without following a
structured technique. Simply stated, the auditor must select sample items without
regard to their size, shape, location, or other physical features.
In using haphazard sampling, the auditor should avoid any conscious bias in the
selection of population items, for example, by selecting only unusual or physically
small items, or omitting the first or last items in a population. Due care must be
exercised in selecting representative samples using this method.
Haphazard selection, however, is not appropriate when using statistical sampling
because it does not allow the auditor to measure the probability of selecting a given
combination of sampling units.
QUESTION 20
ANSWER 20
Block or cluster sampling involves selecting items from the population in contiguous
groups (or blocks).
A block sample is obtained by selecting several items in sequence. Once the first item
in the block is selected, the remainder of the block is chosen automatically. For
instance, the sample may consist of all vouchers processed during a two-week period
or all vouchers processed on specific days. Block samples could theoretically be
representative samples but are rarely used because they are inefficient. The time and
expense to select sufficient blocks so that the samples could be considered
representative of the total population is absurd.
Block sampling is considered the least desirable for use by the auditor and, like
haphazard sampling, is also inappropriate for statistical sampling.
Haphazard selection, however, is not appropriate when using statistical sampling
because it does not allow the auditor to measure the probability of selecting a given
combination of sampling units.
QUESTION 21
ANSWER 21