统计与管理学院2016年学术报告第30期

【主  题】EM Algorithm for Generalized Odds-Rate Models with Interval Censored Data

【报告人】 Zhang Jiajia 教授

University of South Carolina

【时  间】 2016年6月20日（星期一）10:00－11:00

【地  点】 上海财经大学统计与管理学院大楼1208室

【摘  要】The generalized odds-rate models are a special class of linear transformation models, which include the proportional hazards and proportional odds models as special cases. There are few works on efficient estimation of the generalized odds-rate models with interval censored data due to the challenges in maximizing the likelihood function. In this paper, we propose a gamma-Poisson data augmentation approach to characterize the likelihood function and then use an EM algorithm to derive efficient estimation for the generalized odds-rate models with interval censored data. The proposed gamma-Poisson data augmentation greatly simplifies the EM estimation and enhances the computational speed. The performance of the proposed method is evaluated by comprehensive simulation studies and illustrated through applications to datasets from breast cancer and hemophilia studies. An R package “ICGOR” is developed for public use based on the proposed method.

【邀请人】 赵海兵