Parameter Estimation of AFT Model with Informatively Interval-Censored Data
王淑影 1刘舒也 1张亚男 1程云飞1
扫码查看
点击上方二维码区域，可以放大扫码查看
作者信息
1. 长春工业大学数学与统计学院,吉林长春 130012
折叠
摘要
在生存分析研究中,多数文章假定感兴趣的失效时间和删失时间是独立的,但这一假设在实际情况中未必合理.如果忽略失效时间与删失时间的相依性,可能会导致错误的结论.所以本文考虑在带有信息的K型区间删失数据下,采用基于两步估计的极大似然估计方法对误差项服从标准正态分布的加速失效时间模型(accelerated failure time model,AFT)进行参数估计.同时还进行了数值模拟以验证提出方法的有效性.最后,应用所提出的方法分析艾滋病的临床试验数据.
Abstract
For the research of survival analysis,most of existing approaches assume that the censored time is independent of the failure time of interest and it is clear that this may not be true in practice.If we ignore the dependence between the failure time of interest and the censored time,which may cause wrong conclusions.In this article,we consider a general type of censored data,the informatively case K interval-censored data.For the problem,a maximum likelihood estimation approach based on a two-step procedure is proposed to estimate the parameters of accelerated failure time(AFT)model whose error item follows the standard normal distribution.A simulation study is conducted to assess the effectiveness of the proposed method and indicates that it works well.Finally,the method is applied to a set of real data from AIDS clinical trail.
关键词
加速失效时间模型/带有信息的K型区间删失数据/极大似然估计法
Key words
AFT model/informative case K interval-censored data/maximum likelihood estimation
维普
万方数据