Estimating a treatment effect with the accelerated hazards models

In randomized clinical trials, when the outcome of interest is time to event, the proportional hazards model or the accelerated failure time model is often used to identify a treatment effect, In this article, we discuss a simple alternative called the accelerated hazards model in which the treatment effect is characterized as the hazard progression time ratio, when the treatment is believed to accelerate or decelerate the underlying hazard progression through time. Survival data from an actual randomized placebo-controlled trial, which evaluates the effectiveness of biodegradable polymers with carmustine to treat malignant gliomas, is used for illustration. (C) Elsevier Science Inc. 2000.