Large sampling uncertainty is generally introduced in the calculation of a low percentile of fatigue crack growth life due to a small number of coupon tests. It is often desirable to estimate a low percentile (for example, 10th percentile) with a certain coverage probability (for example, 95%) using the confidence bound approach. An equally competing objective is not to have overly conservative bounds.The performance of two bootstrap-based methods are investigated for calculating a one-sided 95% confidence bound on a low percentile of lognormal and gamma fatigue crack growth life distributions. A comparison is also made with the classical tolerance interval method and nonparametric (Hanson-Koopmans) method. These confidence bounds methods are tested to estimate B-basis fatigue crack growth design life using material properties estimated from coupon test samples ranging from 8 to 64.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.