Bayesian inspection model with the negative binomial prior in the presence of inspection errors

Document Type

Article

Publication Date

11-1-2007

Abstract

One of the basic assumptions in Bayesian inspection models is that we have some prior knowledge about the number of defects in a certain product or software system. The prior knowledge can be often described as a probability distribution (e.g., Poisson distribution). In the paper, we propose three conditions that should be put forth as desirable properties for a prior probability distribution of the number of defects in the product. We review various prior probability distributions and test if they meet those conditions. The negative binomial distribution is found to be the only one that satisfies all the desirable conditions. With the negative binomial prior, we analyze the effects of various parameters on the Bayesian estimate of the number of undetected errors still remaining in the product. © 2006 Elsevier B.V. All rights reserved.

Publication Source (Journal or Book title)

European Journal of Operational Research

First Page

1188

Last Page

1202

This document is currently not available here.

Share

COinS