DESIGN, TESTING AND ESTIMATION IN COMPLEX EXPERIMENTATION. II. RELIABILITY GROWTH PROCESSES: ESTIMATION THEORY AND DECISIONTHEORETIC FORMULATIONS.
Final rept. for period ending Feb 65,
ROCKETDYNE CANOGA PARK CALIF
Pagination or Media Count:
Properties of maximum-likelihood estimators of parameters of reliability growth processes are investigated. It is shown that the maximum-likelihood estimator for a simple process involving a single failure mode is not consistent. For a modification of this process, a proof of consistency is sketched. Decision-theoretic studies of reliability growth have included investigations of the minimum-loss redesign policy, single-stage improvement models, and optimum effort for reliability growth. Author