More accurate breakdown voltage estimation for the new step-up test method in the Weibull model

The estimation problems for the conventional step-up method (the observed breakdown voltages are not given at all) and the new step-up method (some of the observed breakdown voltages are given) are analyzed when the underlying probability distribution is assumed to be a Weibull model. This paper is a consecutive research of the case that the underlying probability distribution is assumed to be a normal model. Similarly to the normal model, the new step-up test method, in the Weibull model, also has advantages compared to the conventional method: (1) the confidence intervals of the estimates become smaller and (2) the estimates can be obtained with higher probability. The bias observed when sample size is small can be reduced by using the bootstrap method.