Maximum likelihood estimation for life distributions with competing failure modesThe general model for the competing failure modes assuming that location parameters for each mode are expressible as linear functions of the stress variables and the failure modes act independently is presented. The general form of the likelihood function and the likelihood equations are derived for the extreme value distributions, and solving these equations using nonlinear least squares techniques provides an estimate of the asymptotic covariance matrix of the estimators. Monte-Carlo results indicate that, under appropriate conditions, the location parameters are nearly unbiased, the scale parameter is slightly biased, and the asymptotic covariances are rapidly approached.
Document ID
19790065515
Acquisition Source
Legacy CDMS
Document Type
Conference Paper
Authors
Sidik, S. M. (NASA Lewis Research Center Cleveland, Ohio, United States)
Date Acquired
August 9, 2013
Publication Date
August 1, 1979
Subject Category
Statistics And Probability
Meeting Information
Meeting: American Statistical Association, Annual Meeting