Models and Software Development For Interval-Censored Data

摘要: Interval-censored time-to-event data occur naturally in studies of diseases where the symptoms are not directly observable, and periodic lab or clinical examinations required for detection. Due to lack well-established procedures, interval-censored have been conventionally treated as right-censored data, however, this introduces bias at first place. This dissertation focuses on methodological research software development data. Specifically, it consists three projects. The project is create an R package regression analysis survival curve estimation based several published papers by our team. In second project, a Bayesian semiparametric proportional hazards model with spatial random effect developed spatially correlated third we propose multivariate frailty clustered failure times, which analogous mixed analysis.