A Concise Algorithm for Determining Sample Sizes for Inspections

A model to determine multi-level sample size distributions necessary to achieve certain detection goals is presented here. The model deals with both random and systematic errors and allows a flexible rejection limit. In particular, when binomial approximation is used, the solutions for the sample sizes to achieve a stipulated detection probability goal are expressed in a closed, analytical form. The results obtained are compared with those obtained with the existing method used in international safeguards.