CPA Exam AUD: Audit Sampling Techniques and Methods
Master audit sampling for the CPA AUD exam. Covers statistical and nonstatistical sampling, attribute sampling, variables sampling, and sampling risk.
Audit Sampling Techniques: A Comprehensive CPA Exam Review
Audit sampling is governed by AU-C Section 530 and is a core testable area on the AUD section. Sampling involves applying audit procedures to less than 100% of items within a population when the auditor intends to draw conclusions about the entire population based on the sample results. Understanding sampling methods, risks, and evaluation is essential for CPA exam success.
Statistical vs. Nonstatistical Sampling
Both statistical and nonstatistical sampling are acceptable under GAAS. Statistical sampling uses the laws of probability to select samples and evaluate results, providing a quantitative measure of sampling risk. Nonstatistical sampling relies on the auditor's professional judgment to select samples and evaluate results. While statistical sampling provides a mathematical measure of sampling risk, both approaches require professional judgment in planning, performing, and evaluating the sample.
Sampling Risk
Sampling risk is the risk that the auditor's conclusion based on a sample may differ from the conclusion that would be reached if the entire population were tested. There are two types of sampling risk for each type of test:
For tests of controls:
- Risk of assessing control risk too low (risk of overreliance): The auditor concludes that controls are more effective than they actually are. This affects the effectiveness of the audit because the auditor may reduce substantive testing inappropriately.
- Risk of assessing control risk too high (risk of underreliance): The auditor concludes that controls are less effective than they actually are. This affects the efficiency of the audit because the auditor performs more substantive testing than necessary.
For substantive tests (tests of details):
- Risk of incorrect acceptance: The auditor concludes that a material misstatement does not exist when it actually does. This affects audit effectiveness and is the primary concern.
- Risk of incorrect rejection: The auditor concludes that a material misstatement exists when it actually does not. This affects audit efficiency.
Nonsampling risk is the risk that the auditor reaches an incorrect conclusion for any reason not related to sampling risk, such as using inappropriate audit procedures or failing to recognize a misstatement in a document examined.
Attribute Sampling
Attribute sampling is used primarily for tests of controls. The auditor is testing whether a control was applied (a yes/no attribute). The key steps include defining the attribute of interest (for example, whether an invoice has an approval signature), defining the population and sampling unit, determining the sample size based on the expected deviation rate, tolerable deviation rate, and acceptable risk of overreliance, selecting the sample using a random selection method, performing the test and evaluating deviations found, and forming a conclusion about the population deviation rate.
Sample size in attribute sampling increases when the tolerable deviation rate decreases, when the expected population deviation rate increases, when the acceptable risk of overreliance decreases, and when the population is very large (though for large populations, size has minimal effect).
Variables Sampling
Variables sampling is used for substantive tests of details to estimate the amount of a misstatement or the total dollar value of a population. Common methods include mean-per-unit estimation (estimates the population value by multiplying the sample average by the number of items in the population), difference estimation (estimates the total misstatement by multiplying the average difference between audited and book values in the sample by the population size), and ratio estimation (estimates the population value using the ratio of audited values to book values in the sample applied to the total book value).
Difference and ratio estimation are most effective when differences between audited and book values are expected and when those differences correlate with the book value of the items.
Probability-Proportional-to-Size (PPS) Sampling
PPS sampling, also known as monetary unit sampling or dollar unit sampling, is a commonly used statistical sampling technique for substantive testing. Each individual dollar in the population is treated as a sampling unit. This method automatically results in a stratified sample because larger dollar items have a greater probability of selection. PPS sampling is most effective for testing for overstatement because it is designed to detect items where the recorded amount exceeds the actual amount. It is less effective for testing understatements or zero-balance items, which have no chance of selection.
Sample Selection Methods
Common selection methods include random selection (every item has a known probability of selection), systematic selection (selecting every nth item after a random start), haphazard selection (selection without any structured technique, attempting to approximate random selection), and block selection (selecting a contiguous block of items, which is generally the least representative method).
Evaluating Sample Results
After performing the audit procedures on the sample, the auditor must evaluate the results. For attribute sampling, the auditor compares the sample deviation rate to the tolerable deviation rate. If the sample deviation rate exceeds the tolerable rate, the auditor cannot rely on the control. For variables sampling, the auditor projects the misstatement found in the sample to the population and determines whether the projected misstatement, combined with other known misstatements, exceeds tolerable misstatement.
Exam Tips for Audit Sampling
- Risk of overreliance and risk of incorrect acceptance affect audit effectiveness and are the auditor's primary concerns.
- PPS sampling favors detection of overstatements, not understatements.
- Attribute sampling is for controls testing; variables sampling is for substantive testing.
- Larger samples are needed when tolerable deviation/misstatement is lower or expected deviation/misstatement is higher.
- All items above a certain dollar amount may be individually tested, with sampling applied to the remaining population.
Practice What You Learned
Study with 1,200+ flashcards and 140 practice exams across all 4 CPA sections.