Please use this identifier to cite or link to this item:
http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/22857
Title: | 探討雙截切資料之半母數加速事件時間模型的回歸參數估計 A semi-parametrically accelerated failure time model for doubly-truncated data |
Authors: | Tung-Yang Chou 周東陽 |
Advisor: | 張淑惠(Shu-Hui Chang) |
Keyword: | 雙截切資料,U統計量,半母數加速事件時間模式,可比較配對,類獨立假設, Doubly-truncated data,U-statistic,Semi-parametric accelerated failure time model,Comparable pair,Quasi-independence assumption, |
Publication Year : | 2009 |
Degree: | 碩士 |
Abstract: | 在許多臨床及公共衛生研究中經常會遇到雙截切資料,此資料只有當其事件發生在一段可觀察區段之間才會被觀察。本文考慮以一種可具體說明共變項與事件時間之間的線性關係之半母數加速事件時間模型來模式化其關係。基於上述的模式設定以及事件時間與可觀察區間的類獨立關係,本文發展出一種以U統計量為基礎的估計式以估計回歸係數。在本文所提出的估計方程式中,使用了可比較配對以調整雙截切所產生的偏誤。最後,進行模擬研究以檢視本文提出的方法在有限樣本下的表現。 In many clinical and public health studies, doubly truncated data are frequently encountered, in which the event of interest is observed only if it occurs in an observable interval. We consider a semi-parametrically accelerated failure time model which specifies a linear relationship between the event time and covariates. Based the above model setting and the quasi-independence assumption between event time and the observable interval, we develop a U-statistic-based estimating equation to estimate the regression coefficients. In our proposed estimating equation, comparable pairs are used to adjust the bias of double truncation. Finally, simulation studies are conducted to examine the performance of our proposed method in finite samples. |
URI: | http://tdr.lib.ntu.edu.tw/jspui/handle/123456789/22857 |
Fulltext Rights: | 未授權 |
Appears in Collections: | 流行病學與預防醫學研究所 |
Files in This Item:
File | Size | Format | |
---|---|---|---|
ntu-98-1.pdf Restricted Access | 316.93 kB | Adobe PDF |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.