An OC Curve Describes Acceptance Probability, Not a Quality Guarantee

The statistical question

For a binomial attributes model, acceptance probability is the probability that the sample contains no more than the plan acceptance count. The operating-characteristic curve evaluates that probability over incoming nonconforming proportions. Its use requires the appropriate sampling basis, including when a large-lot approximation is justified. The curve is a property of the plan and model, not an observed lot certificate.

Primary reference: NIST Engineering Statistics Handbook.

An illustrative review example

In a fictional independent-sampling calculation with n=20 and c=0, an incoming nonconforming probability of 0.02 gives acceptance probability 0.98 raised to the twentieth power, about 0.668. At probability 0.10, the same calculation gives 0.90 raised to the twentieth power, about 0.122. Both are hypothetical model results. Finding zero nonconforming items does not mean every item in the corresponding lot is conforming.

Prepare the evidence for discussion

Before asking for an OC calculation, identify n, c, the incoming-quality variable and the lot/population relationship. Label any finite-lot or dependence limitation instead of forcing a binomial approximation. Keep achieved probabilities beside the target protection points. Use this information to compare inspection proposals with the quality team; acceptance of a mechanical component sample still does not demonstrate all machine-interface or production requirements.

An acceptance probability is conditional

This blank worksheet is for your own project. It contains no H M machine trial result.

Customer Questions

Primary References

These references support the technical principles discussed in this guide. The worked examples and review questions are educational.

• Primary reference: NIST Engineering Statistics Handbook