Optimal design of multiple accelerated life testing for generalized half-normal distribution under type-I censoring

Abstract

This article uses three optimality criteria to conclude the optimal allocation of multiple accelerated life testing for the generalized half-normal model under type-I censoring. We derive the maximum likelihood estimates of the parameters and their Fisher information matrix. Numerical and simulations examples are used to demonstrate the effectiveness of the optimal allocation. A sensitivity analysis of the optimal allocation to misspecification of the model parameters is conducted.