Statistical Inference for Reliability from Stress Strength Relationships: The Normal Case.
Abstract
This paper examines statistical inference for P(Y < X), where X and Y are independent normal variates with unknown means and variances. The case of unequal variances is stressed. X can be interpreted as the strength of a component subjected to a stress Y, and P(Y < X) is the components reliability. For point estimation, a predictive estimator which can be calculated from the Behrens-Fisher distribution is derived and compared with the maximum likelihood and uniformly minimum variance unbiased estimators through a simulation study. Two approximate methods for obtaining confidence intervals and an approximate Bayesian probability interval is obtained. The actual coverage probabilities of these intervals is examined by simulation. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- May 01, 1984
- Accession Number
- ADA142893
Entities
People
- B. Reiser
- I. Guttman
Organizations
- University of Wisconsin–Madison