The analysis of tumorigenicity data using a frailty effect |
| |
Authors: | Yang-Jin Kim Chung Mo Nam Youn Nam Kim Eun Hee Choi Jinheum Kim |
| |
Affiliation: | aDepartment of Statistics, Sookmyung Women’s University, Seoul 120-750, Republic of Korea;bDepartment of Preventive Medicine, Yonsei University College of Medicine, Seoul 120-749, Republic of Korea;cDepartment of Epidemiology and Biostatistics, Yonsei University Graduate School of Public Health, Seoul 120-749, Republic of Korea;dDepartment of Biostatistics, Yonsei University College of Medicine, Seoul 120-749, Republic of Korea;eDepartment of Applied Statistics, University of Suwon, Gyeonggi-Do 445-743, Republic of Korea |
| |
Abstract: | In animal tumorigenicity data, the time of occurrence of the tumor is not observed because the existence of the tumor is looked for only at either the time of death or the time of sacrifice of the animal. Such an incomplete data structure makes it difficult to investigate the impact of treatment on the occurrence of tumors. A three-state model (no tumor–tumor–death) is used to model events that occurred sequentially and to connect them. In this paper, we also employed a frailty effect to model the dependency of death on tumor occurrence. For the inference of parameters, an EM algorithm is considered. The method is applied to a real bladder tumor data set and a simulation study is performed to show the behavior of the proposed estimators. |
| |
Keywords: | AMS 2000 subject classifications: primary, 62N01 secondary, 62N02 |
本文献已被 ScienceDirect 等数据库收录! |
|