Choose confidence, error bounds, and defect estimates for sampling. Get acceptance guidance using AQL and risk settings. Download results as CSV and PDF instantly.
| Lot Size (N) | Confidence | Margin (%) | Defect Est. (%) | Sample (n) | AQL (%) | α (%) | c | Reject at |
|---|---|---|---|---|---|---|---|---|
| 500 | 95% | 5 | 10 | 109 | 1 | 5 | 3 | 4 |
| 5,000 | 95% | 3 | 5 | 195 | 1 | 5 | 4 | 5 |
| 20,000 | 99% | 2 | 2 | 320 | 0.65 | 5 | 5 | 6 |
A lot sample is a trade‑off between assurance and inspection effort. This calculator uses confidence (Z) and margin of error (E) to size n for estimating the defect proportion. For example, with N=5,000, 95% confidence, E=3%, and an estimated defect rate of 5%, the sample typically falls near the low hundreds, not thousands. When the estimate is unknown, using 50% makes p(1−p) largest and produces the most conservative n.
If you inspect a meaningful fraction of the lot, finite population correction reduces the required sample because each inspected unit removes uncertainty from the remaining pool. The correction is most noticeable for small lots. For instance, a computed n₀=400 on a lot of N=500 is adjusted downward by FPC, preventing over‑inspection while keeping the same confidence and error target.
The acceptance number c connects sampling to pass/fail decisions. Using a binomial model, this tool selects the smallest c where P(X≤c | p=AQL) ≥ 1−α. With AQL=1.0% and α=5%, the plan aims to reject good lots no more than 5% of the time. LTPD provides a consumer‑side check: if P(accept | LTPD) is above your β target, increase n or tighten the decision threshold.
Expected defects are calculated as n·p and help with staffing and rework planning. A sample of n=200 at an estimated 2% defect rate implies about 4 defects on average, but actual counts vary. Use this estimate to allocate inspection time, confirm spare parts availability, and set escalation triggers for repeated nonconformance.
In supplier qualification, keep a stable confidence and error policy so results are comparable across months. In internal audits, export the CSV for traceability and the PDF for sign‑off packets. When standards require specific sampling tables, use this calculator for planning and sensitivity checks, then document the final plan that matches your governing procedure.
It is the number of units to inspect to estimate the defect rate within your chosen margin of error at the selected confidence level, adjusted for finite lot size.
Use 50% when historical defect data is missing or unreliable. It yields the largest sample for a given confidence and error target, providing a conservative inspection plan.
The tool searches for the smallest c such that the probability of accepting a lot at the AQL is at least 1−α, using a binomial model.
If P(accept | LTPD) is higher than your β target, the plan is too lenient. Increase sample size, lower c, or use a stricter LTPD.
No. It supports planning, sensitivity checks, and documentation. If your organization follows a specific standard, validate the final sample plan against that standard’s tables and procedures.
Export the PDF for sign‑off, attach the CSV to your inspection record, and note the inputs used (N, confidence, margin, AQL, α, LTPD, β) so the plan can be reproduced exactly.
Important Note: All the Calculators listed in this site are for educational purpose only and we do not guarentee the accuracy of results. Please do consult with other sources as well.