Chapter 2 Inference for one-shot devices with a single failure mode ⍟ ⍟ This book has a companion website hosting complementary materials. Visit this URL to access it: https://data.mendeley.com/datasets/879xmdz3d8/1.

Much work has been carried out in recent years concerning one-shot device testing assuming a single cause of failure. In this chapter, we present a comprehensive overview of both parametric and non-parametric estimation methods developed for this type of data under constant-stress accelerated life tests (CSALTs). We describe the classical likelihood inference, its associated confidence intervals and hypothesis tests, and discuss the problem of model misspecification when presuming which distribution is associated with our data. We also describe the Bayesian inferential method, considering different prior distributions. Finally, we provide a brief explanation of two non-parametric inferential methods for the analysis of one-shot device testing data.