Simple step-stress models with a cure fraction (Q2180252)

Motivated by many applications in physical, environmental, and biomedical sciences, the authors consider models for time-to-event data obtained from experiments in which stress levels are altered at intermediate stages during the observations period. These experiments are known as step-stress tests in the reliability literature. The analysis of data from step-stress tests relies on a cumulative exposure model and despite its simplicity, it is limited due to the underlying assumption that the hazard function of the underlying distribution is discontinuous at the points where the stress levels are changed. This may limit the applications to a reasonable extent. To overcome this deficiency, \textit{N. Kannan} et al. [J. Appl. Stat. 37, No. 10, 1625--1636 (2010; Zbl 07252534)] introduced the cumulative risk model, where the hazard function is continuous. In this paper, the authors propose a class of parametric models based on the cumulative risk model assuming the underlying population contains long-term survivors or cured fraction. This work is motivated by a study on altitude decomposition sickness. The performance of different parametric models are evaluated using data from this study.