Regression analysis of interval-censored failure time data

Interval-censored failure time data often occur, for example, in clinical trials or longitudinal studies. For the regression analysis of such data, there have been a number of methods proposed based on continuous regression models such as Cox's proportional hazards model. In practice, however, observed interval-censored data that arise from clinical trials are often given in a discrete scale due to the nature of clinical trials although the underlying variable may be continuous. It is apparent that in this case, one can better handle analysis of the data with the methods based on discrete models. In this paper, I propose a method based on a discrete logistic model for the regression analysis of interval-censored failure time data with focus on the comparison of failure time distributions among different treatments. I discuss the relationship between the proposed method and existing methods.