Curtailed Attribute Sampling

Publisher Website
Google Scholar
Abstract
This paper is concerned with maximum likelihood estimation of a process (or lot) average proportion of defectives based on attribute samples that have been curtailed either with rejection of a lot on finding the kth defective or with acceptance on finding the Kth nondefective. The MLE, , based on inspections from a sequence of m lots is shown to be simply the ratio of the number of defectives found to the total number of items inspected, and the asymptotic variance of this estimator is shown to be approximately (1 — )/Σ m 1 y i , where Σ m 1 y i is the total of all items inspected.

This publication has 0 references indexed in Scilit: