Optimal bivariate step-stress accelerated life test for Type-I hybrid censored data
Authors:
- 1 September 2011
- journal article
- research article
- Published by Taylor & Francis in Journal of Statistical Computation and Simulation
- Vol. 81 (9) , 1175-1186
Abstract
This paper presents a step-stress accelerated life test for two stress variables to obtain optimal hold times under a Type-I hybrid censoring scheme. An exponentially distributed life and a cumulative exposure model are assumed. The maximum-likelihood estimates are given, from which the asymptotic variance and the Fisher information matrix are obtained. The optimal test plan is determined for each combination of stress levels by minimizing the asymptotic variance of reliability estimate at a typical operating condition. Finally, simulation results are discussed to illustrate the proposed criteria. Simulation results show that the proposed optimum plan is robust, and the initial estimates have a small effect on optimal values.Keywords
This publication has 12 references indexed in Scilit:
- Design of accelerated life test sampling plans with a nonconstant shape parameterEuropean Journal of Operational Research, 2009
- Optimal simple step stress accelerated life test design for reliability predictionJournal of Statistical Planning and Inference, 2009
- Exact inference for a simple step-stress model with Type-I hybrid censored data from the exponential distributionJournal of Statistical Planning and Inference, 2007
- Optimum Bivariate Step-Stress Accelerated Life Test for Censored DataIEEE Transactions on Reliability, 2007
- Optimal Step-Stress Test Under Progressive Type-I CensoringIEEE Transactions on Reliability, 2004
- Planning step-stress life-test with a target acceleration-factorIEEE Transactions on Reliability, 1999
- Optimum M-step, step-stress design with K stress variablesCommunications in Statistics - Simulation and Computation, 1997
- Optimum 3-step step-stress testsIEEE Transactions on Reliability, 1996
- Optimum simple step-stress accelerated life tests with censoringIEEE Transactions on Reliability, 1989
- Truncated Life Tests in the Exponential CaseThe Annals of Mathematical Statistics, 1954