有關右設限事件時間資料大多數文獻已探討迴歸參數之先驗分佈的擇優問題以及由後 驗分佈得到一些計算方法(例如: Sinha and Dey, 1997; Ibrahim et al., 2001; Kalbfleisch, 1978)。另一方面,針對區間設限資料僅少數研究提及(例如: Sinha et al., 1999; Hanson and Johnson, 2004)。 Chen et al. (2007) 、Tong et al. (2008) 和 Chen et al. (2009) 考慮區間設限資料之半參數 迴歸分析,其中假設風險函數屬於線性函數空間。本計畫中,我們聚焦於藉由經驗貝 氏方法來處理區間設限資料之未知基線風險函數。我們將藉由存活資料集的分析以及 模擬的結果來說明我們所提出方法的優點。 A voluminous literature on right-censored failure time data has been discussed for selecting a prior distribution of regression parameters and obtaining some computational methods to sample from the posterior distribution (Sinha and Dey, 1997; Ibrahim et al., 2001; Kalbfleisch, 1978). On the other hand, for interval-censored data, there exists much less research due to the difficulties introduced by such censoring (Sinha et al., 1999; Hanson and Johnson, 2004). Chen et al. (2007) , Tong et al. (2008), Chen et al. (2009) considered semiparametric regression analysis of the interval-censored data assuming that the hazard function belongs to a linear function space. In this project, we focus at this unknown baseline hazard function by empirical Bayesian approaches for dealing interval-censored data. We are going to illustrate the advantages of our methodology with a reanalysis of a survival dataset and a simulation study.