## Three Steps in Audit Sampling

1. Design – Consider purpose of the audit procedure + characteristics of the population

2. Size – Determine sample size sufficient to reduce sampling risk to an acceptably low level

Lower acceptable risk → larger sample required

3. Select – Choose items so that each sampling unit has a chance of selection (unbiased method)

---

## Statistical vs Non-Statistical Sampling

Dimension	Statistical	Non-Statistical
Basis	Mathematical laws of probability	Auditor's personal experience and judgment
Projection	Can mathematically project to population	Cannot formally project
Objectivity	High — defensible	Subjective

Both are permitted under SA 530. The choice is a matter of auditor judgment.

---

## Advantages of Statistical Sampling (Mnemonic: BMC PAO)

Letter	Advantage
B	Better description of a large mass of data
M	Means of estimating minimum sample size for a specified risk and precision
C	Calculated risk (sampling error) — probable difference due to sampling — can be derived
P	Sample size does NOT increase proportionately with population size
A	Widely Accepted method
O	More Objective and therefore more defensible

Worked example

### Example 1

Auditor uses systematic random selection: random start = Invoice #47, interval = 20. Items tested: #47, #67, #87, #107… Every item has an equal chance of selection — satisfying the unbiased requirement of SA 530.

### Example 2

An auditor uses non-statistical judgment sampling, selecting 'suspicious-looking' invoices. While this may catch errors, findings cannot be mathematically projected to the population — the sample is biased by the auditor's preconceptions. No calculated risk can be stated.

⚠️ Common exam mistakes

Treating non-statistical sampling as inferior or non-compliant — SA 530 permits both; the difference lies in the ability to mathematically project results
Equating 'random selection' with 'statistical sampling' — random selection is a picking technique; statistical sampling also requires mathematical projection of results to the population
Assuming larger population always needs proportionally larger sample — the 'P' in BMC PAO highlights that this proportionality does NOT hold

Reference: — SA 530 – Audit Sampling

Now that you've read this — what's next?

Move from understanding → mastery in 3 clicks. Each option below picks up from this lesson's topic.

🔥 Drill 5 Qs on this → ✍️ Adaptive practice →

Sample Design, Selection Methods, and Statistical vs Non-Statistical Sampling

Worked example

⚠️ Common exam mistakes