Premium
Estimating component characteristics from system failure‐time data
Author(s) -
Bhattacharya Debasis,
Samaniego Francisco J.
Publication year - 2010
Publication title -
naval research logistics (nrl)
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.665
H-Index - 68
eISSN - 1520-6750
pISSN - 0894-069X
DOI - 10.1002/nav.20407
Subject(s) - estimator , bar (unit) , component (thermodynamics) , nonparametric statistics , inverse , mathematics , parametric statistics , function (biology) , confidence interval , statistics , survival function , maximum likelihood , asymptotic distribution , computer science , discrete mathematics , physics , geometry , evolutionary biology , biology , meteorology , thermodynamics
Suppose that failure times are available from a random sample of N systems of a given, fixed design with components which have i.i.d. lifetimes distributed according to a common distribution F . The inverse problem of estimating F from data on observed system lifetimes is considered. Using the known relationship between the system and component lifetime distributions via signature and domination theory, the nonparametric maximum likelihood estimator $ \hat{ \bar{F}} $ N ( t ) of the component survival function $ \bar{F} $ ( t ) is identified and shown to be accessible numerically in any application of interest. The asymptotic distribution of $ \hat{ \bar{F}} $ N ( t ) is also identified, facilitating the construction of approximate confidence intervals for $ \bar{F} $ ( t ) for N sufficiently large. Simulation results for samples of size N = 50 and N = 100 for a collection of five parametric lifetime models demonstrate the utility of the recommended estimator. Possible extensions beyond the i.i.d. framework are discussed in the concluding section. © 2010 Wiley Periodicals, Inc. Naval Research Logistics, 2010