Abstract

In accelerated life testing, statistics-based accelerated models can be divided into parametric models and non-parametric models. Non-parametric models are followed more closely because of the distribution free property. Proportional hazards model and proportional odds model are two widely used non-parametric models. However, the assumptions of these models are not satisfied sometimes. Many generalized models are presented based on these models to deal with the cases that the assumptions of these models are violated. One example is the proportional hazards-proportional odds model. It makes proportional hazards model and proportional odds model special cases of it through a transformation parameter. This paper extends the proportional hazards-proportional odds model to a more generalized model which reflects time scale changing effects and time varying coefficient effects. Simulations are processed to verify this model.

Full Text
Published version (Free)

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call