Parameters Estimation for Constant-Stress Partially Accelerated Life Tests of Generalized Half-Logistic Distribution Based on Progressive Type-II Censoring

Abstract

In product-life testing experiments, the accelerated life testing (ALT) is applied to reduce the time and cost of tests. We consider the constant-stress partially ALT model when the lifetime of units under normal conditions follow the generalized half-logistic lifetime distribution based on progressive Type-II censored schemes. The likelihood functions of the parameters are derived and solved to present the maximum likelihood estimators of the model parameters. The approximate and two bootstrap confidence intervals are also proposed. The performance of the different methods were measured and compared through Monte Carlo simulation study. Finally, the results of a numerical example are discussed.

Keywords

• constant-stress partially accelerated life tests
• generalized half-logistic distribution
• maximum likelihood estimation
• bootstrap confidence intervals