You are on page 1of 6

Audit Sampling in Substantive Testing

Variable Sampling

Classical Variables Sampling Models use normal distribution theory to evaluate selected characteristics
of a population on the basis of a sample of items constituting the population.

Classical Variables Sampling plans enable auditors to estimate a numerical quantity, such as the peso
amount of an account balance. This makes these techniques particularly useful for performing
substantive procedures. Classical variables sampling methods include mean-per-unit estimation, ratio
estimation, and difference estimation.

MEAN-PER-UNIT ESTIMATION

-enables auditors to estimate the mean audited value of the items in a population, with specified
sampling risk and allowance for sampling risk, by determining the mean audited value of the items in a
sample. An estimate of the total audited value of the population is obtained by multiplying the sample
mean (the average audited value in the sample) times the number of items in the population. The
projected misstatement (the most likely amount of misstatement in the population) may then be
calculated as the difference between this estimated total audited value and the client’s book value. The
assumption underlying mean-per-unit estimation is that sample’s mean audited value will, for a certain
sampling risk and allowance for sampling risk, represent the true audited mean of the population.
Variable sampling is known by estimation sampling. In variable sampling, we’re looking at the money
amount, we’re estimating the money value of the population not the deviation. We use the deviation
when we are testing for internal control.
I’m going to show you how to calculate the implied audit value for a population by using mean per unit
estimation. So, let’s say that we’re auditing accounts payable. We’ve got the following data here. We’ve
got a population as 6500 accounts payable and they have a book value of 6025500 and then we draw a
sample of 500 accounts which have a book value of 450000 and we find that the audit value of these
500 accounts payable is actually 462000. The question is what is the audit value for the entire
population. We didn’t observe the population but now we can find what the implied audit value is from
the data that we have here.

So, we’ve got a 2-step procedure with mean per unit estimation.

First, we’re going to take the audit samples value which is 462000 and then we’re going to divide it by
the number of accounts in the sample 500. So, we are going to take 462000 and divide it by 500 and
that’s going to equal 924. In this 924, that is our mean per unit.

And now that we know our mean per unit, let’s multiply it by the number of accounts in the population
which is 6500. Equals to 6006000, this is now our implied audit value for the entire population
Audit Sampling in Substantive Testing

Variable Sampling

Classical Variables Sampling Models use normal distribution theory to evaluate selected characteristics
of a population on the basis of a sample of items constituting the population.

Classical Variables Sampling plans enable auditors to estimate a numerical quantity, such as the peso
amount of an account balance. This makes these techniques particularly useful for performing
substantive procedures. Classical variables sampling methods include mean-per-unit estimation, ratio
estimation, and difference estimation.

So were going to talk about Steps involve in variable sampling

Variable sampling on the other hand is concerned on the amounts of the account balances.

So here are the different steps:

1. The auditor should determine the objective of a certain test


- Variable sampling is normally used for substantive testing because in this case the auditor is
concerned about the values or the amounts of the accounts; and its conclusion is generally stated in
terms of pesos and quantities.

2. So, after the auditor determine his objective, he will define the population where the samples will
be taken.
- The population should consist of the items constituting the account balance or class of transaction
of interest.
- Items that are individually significant for which sampling risk is not justified should be tested
separately and not be subjected to sampling because in this case there might be a division that exist
there that’s why it should be separately tested.
3. The next step is to select an audit sampling technique
- The auditor may select either the value weighted selection which also is called (probability
proportional to size sampling) or classical variables sampling.
4. Next, he will determine the sample size (n).
- The auditor should consider the factors that affect the sample size for substantive procedures.
5. Next step is the auditor will determine the method of selecting the sample.
- Usually, random number or systematic sampling is used.
6. Then the auditor will perform the sampling plan.
- The auditor should perform appropriate audit procedures to determine an audit value for each
sample size.
7. Then after that, he will evaluate the sample results.
- The auditor should project the results of the sample to the population if indeed the results can be
inferred to the population.
8. Lastly, he has to document the sampling procedure.
- Each of the prior steps and the conclusions reached should be documented in the working papers.
- This will serve as a proof and support on his audit opinion and he may also use that in his future
engagement as well

We’ll continue with the next topic which is about Factors in Determining the Sample Size for
Substantive Tests of Details – what are the factors that the auditor needs to consider for the sample
size.

- Auditor’s assessment of risk of material misstatement:

The higher the auditor’s assessment of the risk of material misstatement (meaning this is based on the
inherent and control risk), the lower the level of detection risk that the auditor can accept. Because in
this case he should lower his detection risk so that the overall audit risk will also be lowered. What does
this mean? Meaning if assessed risk of material misstatement is high, the auditor has to do more
substantive procedures to gather more audit evidences to detect misstatement.

Hence, the auditor should increase the extent (sample size) of substantive tests of details.

- Use of other substantive procedures directed at the same financial statement assertion

The more the auditor relies on other substantive procedures (such as analytical procedures) to reduce
the detection risk to an acceptable level, the less assurance the auditor will require from sampling, and
as a result, sample size for substantive test of details can be reduced.

- Auditor’s required confidence level and risk of incorrect acceptance

What is incorrect acceptance-IS WHEN the auditor relied on the internal controls of the entity

An increase in the auditor’s degree of confidence level (or conversely, a decrease in the risk of incorrect
acceptance) will result to an increase in the sample size for substantive tests of details.

For substantive tests of details, the auditor’s required confidence level refers to the level of assurance
that the auditor requires that the results of the sample are in fact indicative of the actual amount of
misstatement in the population.

- Tolerable misstatement

Tolerable misstatement refers to a monetary amount set by auditor in respect of which the auditor
seeks to obtain an appropriate level of assurance that the monetary amount set by the auditor is not
exceeded by the actual misstatement in the population.

The lower the tolerable misstatement, the larger the sample size for substantive tests of details needed

Stated differently, tolerable misstatement is an estimate of the maximum monetary misstatement that
may exist in an account balance or class of transaction, when combines with misstatement in other
accounts, without causing the financial statements to be materially misstated.

- Expected amount misstatement


The expected amount of misstatement is the amount of misstatement the auditor expects to find in the
population.

It is usually estimated based on the auditor’s understanding of the client’s business, prior year
information, or the results of the review and evaluation of internal control.

The greater the expected amount of misstatement, the larger the sample size needed in order to make
a reasonable estimate of the actual amount of error in the population.

- Stratification

When there is variability in the monetary size of the items in the population, it may be appropriate to
stratify the population.

When a population can be stratified, the aggregate of the sample sizes from the strata generally will be
less than the sample size that would have been required had the sample been drawn from the whole
population.

- Number of Sampling Units in the population

Sample size normally increases as population size increase. For large populations, however, the actual
size of the population has little, if any, effect on sample size.

You might also like