Bootstrap-Based Confidence Intervals in Partially Accelerated Life Testing Under the Generalized Exponential Distribution

• Activity Number: 266
• Type: Contributed
• Date/Time: Monday, August 10, 2015 : 2:00 PM to 3:50 PM
• Sponsor: Quality and Productivity Section
• Author(s): Ahmed Eshebli* and V.A. Samaranayake
• Companies: Missouri University of Science and Technology and Missouri University of Science and Technology
• Keywords: Resampling ; PALT ; Maximum Likelihood ; Accelaration Factor ; Mean Life ; Life Distribution

Abstract

Partially accelerated life testing (PALT) is preferable over accelerated life testing (ALT) in situations where a model linking the stress to the distribution parameters is unavailable. Under the assumption of a generalized exponential life distribution and Type I censoring, a bootstrap-based method of obtaining confidence intervals for the distribution parameters, the acceleration factor, and the mean life, is introduced. Its performance is studied against that of intervals obtained using the traditional delta method, using Monte Carlo simulation. Results show that the bootstrap-based method performs better than the traditional approach.