This paper consider the choice of sample size for experiments concerned with inference on R = P(Y > X) where X and Y are random variables, in an acceptance sampling theory framework. The following cases are considered: X and Y independent exponential variates, X and Y dependent normal variates, X and Y independent normal variables, and the nonparametric case.
Bibliographical noteFunding Information:
The authors thank Boon Ping Chew for programming assistance and a referee for his helpful comments. I. Guttman was supported by a grant from NSERC, through Grant NoA8743. Part of this work was conducted while B. Reiser was visiting the Department of Statistics, Temple University and their kind hospitality is acknowledged.
- acceptance sampling
- sample size
- stress-strength models
ASJC Scopus subject areas
- Statistics and Probability