|
Abstract:
|
In this paper, we develop a model to study treatment, period, carryover, and other applicable effects in a crossover design with time-to-event response variable. Since times-to-event on different treatment arms are correlated for each individual, we adopt a proportional hazard frailty model. In the case when frailty is assumed to have a gamma distribution, and hazard rates are constant on each treatment arm (the latter assumption is reasonable for chronic diseased on a relatively short period of time), the likelihood function for determining parameters of interest can be evaluated in a closed form. We apply the developed model to real data collected from asthma treatment studies.
|
