Estimation of the Reliability of a Stress-Strength System from Power Lindley Distributions.

In this paper, we are interested in the estimation of the reliability parameterR=P(X>Y) where X, a component strength, and Y, a component stress, are independent power Lindley random variables. The point and interval estimation of R, based on maximum likelihood, nonparametric and parametric bootstrap methods, are developed. The performance of the point estimate and confidence interval of R under the considered estimation methods is studied through extensive simulation. A numerical example, based on a real data, is presented to illustrate the proposed procedure. [ABSTRACT FROM AUTHOR]