含有区间删失数据时的生存函数估计及其SAS实现

目的 介绍生存分析中区间删失数据的特点及含区间删失数据生存函数估计的非参数方法,并介绍其在SAS9.2中的程序实现.方法 采用非参数极大似然估计法对Beadle等研究2种疗法对早期乳腺癌患者形体美容效果研究的区间删失数据进行生存函数估计,并利用SAS中的宏程序%EMICM实现其计算.结果 非参数极大似然估计法有效的计算出了2组疗法患者每个个体的生存概率、死亡概率、累积生存概率以及生存率的标准误,绘制出了2组疗法患者的生存曲线.结论 区间删失数据是临床实践中较常见的一类数据,区间删失数据生存函数估计的非参数方法 是常用的一种方法,但其计算相对右删失数据过程复杂,缺乏相应的软件实现,本文提供的SAS宏程序可以有效的实现计算,为实际工作提供帮助.

Estimating survival functions of interval-censored data with SAS

Objective The interval-censored survival data and the estimation of survival functions and the SAS macro procedure were introduced. Methods The NPMLE （ Nonparametric likelihood estimator） was used to estimate the Breast Cancer data presented by Beadle in 1984, and the SAS macro % EMICM was used to compute it. Results The NPMLE of survival functions was computed and the survival curves were drawn by the SAS macro. Conclusion The interval-censored event time data a- rise in many area of studies, methods for analysis of interval censored survival data are complicated and harder to implement than their right-censored eounterparts. The nonparametric methods for the analysis of interval-censored survival data have been surveyed and the SAS macros which have been presented in this paper are useful to these studies.