Interval Estimation for Censored Accelerated Life Tests Based on the Lognormal Model

Abstract

Simulation studies in this paper indicate that the standard large sample confidence intervals applied to censored samples from accelerated life tests tend to be too short for the required confidence level. Alternative confidence limits are derived which are asymptotically equivalent to the standard large sample confidence limits. These new confidence limits are asymmetric for finite-sized samples and produce a more accurate upper confidence limit. If the main point of an investigation is to determine whether the median or percentile lifetime is below a certain value, a one-sided confidence bound can be used and the proposed technique will yield more accurate results.