Likelihood asymptotics for the stress-strength model P(X CORTESE, GIULIANA;VENTURA, LAURA 2009 Abstract A stress-strength model is concerned with the statistical problem of evaluating the reliability parameter R = P(X Scheda breve Scheda completa Scheda completa (DC) Anno 2009 Titolo del Libro Proceedings S.Co.2009: Complex Data Modeling and Computationally Intensive Statistical Methods for Estimation and Prediction Titolo convegno S.Co.2009 Appare nelle tipologie: 04.01 - Contributo in atti di convegno

A stress-strength model is concerned with the statistical problem of evaluating the reliability parameter R = P(X <Y ), where X and Y are taken to be independent random variables. Classical likelihood based procedures for inference on R are available, but it is well-known that they can be inaccurate when the sample size is small, in particular in the presence of many unknown parameters. In this paper, we discuss and apply higher-order likelihood based procedures to obtain accurate confidence intervals for R. The accuracy of the proposed methodology is illustrated by numerical studies.