Chapter 8 Robust inference under the proportional hazards model ⍟ ⍟ This book has a companion website hosting complementary materials. Visit this URL to access it: https://data.mendeley.com/datasets/879xmdz3d8/1.

In this chapter, we introduce a family of robust estimators and Wald-type tests based on the density power divergence (DPD) measure for one-shot device testing under constant-stress accelerated life tests (CSALTs), with a single failure mode under the proportional hazards model. The proportional hazards model allows the hazard rate to vary in a non-parametric manner. The derived DPD-based estimators and Wald-type tests include the maximum likelihood estimator (MLE) and the classical Wald test, respectively, as a particular case. We develop the influence functions (IFs) of the proposed procedures demonstrating their robustness, and also through an extensive simulation study. Finally, a numerical example on electric current data is used to illustrate the developed results.