透過您的圖書館登入
IP:3.22.77.30

並列摘要


This paper discusses regression analysis of clustered current status data which occur if the failure time of interest in a cluster survival study is either left-or right-censored, or each subject is observed only once. Some examples of the areas that often produce such data are cross-sectional studies and tumorigenicity experiments (Keiding [14]; Sun [22]). A few methods have been developed if the failure time of interest is only right-censored, but there does not seem to exist a method for current status data. For the problem, we present a Cox frailty model and a two-step EM algorithm is developed for parameter estimation. A simulation study is conducted for the evaluation of the proposed methodology and indicates that the approach performs well for practical situations. An illustrative example from a tumorigenicity experiment is provided.

延伸閱讀