| Population | 90% | 95% | 99% |
|---|---|---|---|
| 100 | 49 | 80 | 87 |
| 500 | 72 | 176 | 250 |
| 1,000 | 77 | 213 | 358 |
| 5,000 | 81 | 253 | 476 |
| 10K | 82 | 260 | 498 |
| 50K | 83 | 267 | 517 |
| 100K | 83 | 268 | 520 |
SA 530 — "Audit Sampling" — provides the framework for designing, selecting, and evaluating audit samples. Sampling is the application of audit procedures to less than 100% of the items within a population such that all sampling units have an equal chance of selection, in order to provide the auditor with a reasonable basis on which to draw conclusions about the entire population.
Two broad approaches: statistical and non-statistical. Statistical sampling uses probability theory (Monetary Unit Sampling / MUS, Classical Variables Sampling) — sample size is calculated from confidence level, tolerable misstatement, and expected misstatement. Non-statistical sampling uses professional judgement but follows the same logical principles. Both must give all items an equal chance of selection.
Sample size is driven by: (a) the auditor's desired confidence level (typically 90-95%), (b) the tolerable misstatement (typically tied to performance materiality), (c) the expected misstatement in the population (from prior years or interim findings), and (d) the assessed risk of material misstatement. Higher risk → larger sample. Tests of controls follow attribute sampling (yes/no — control operated as designed); tests of details follow monetary sampling.
A company has 3,500 trade receivable balances totaling ₹50 cr. Performance materiality is ₹40 lakh. Expected misstatement based on prior year is ₹5 lakh. Risk assessment is "moderate".
