English  |  正體中文  |  简体中文  |  全文筆數/總筆數 : 49633/84879 (58%)
造訪人次 : 7690943      線上人數 : 79
RC Version 7.0 © Powered By DSPACE, MIT. Enhanced by NTU Library & TKU Library IR team.
搜尋範圍 查詢小技巧:
  • 您可在西文檢索詞彙前後加上"雙引號",以獲取較精準的檢索結果
  • 若欲以作者姓名搜尋,建議至進階搜尋限定作者欄位,可獲得較完整資料
  • 進階搜尋
    請使用永久網址來引用或連結此文件: http://tkuir.lib.tku.edu.tw:8080/dspace/handle/987654321/87464


    題名: 現狀數據在比例風險模型下之概似比檢定
    其他題名: Likelihood ratio test for proportional hazards model with current status data
    作者: 陳俊緯;Chen, Jyun-Wei
    貢獻者: 淡江大學數學學系碩士班
    溫啟仲;Wen, Chi-Chung
    關鍵詞: 概似比檢定;比例風險模型;現狀數據資料;自身一致方程式;Likelihood Ratio Test;Proportional hazards Model;Current Status Data;self-consistency equations
    日期: 2012
    上傳時間: 2013-04-13 11:10:02 (UTC+8)
    摘要: 現狀設限毀壞時間的觀察數據包含檢查時間和毀壞事件發生時間是否在檢查時間之前發生。在現狀數據中,有關於毀壞事件發生時間和共變量之間的關係的數個半母數迴歸方法,已被廣泛地研究。在本論文中,我們考慮在比例風險模型下之現狀數據,對於共變量效應之概似比檢定。並提出一個可以簡單執行的演算法來計算此檢定量。此演算法是根據一系列的自身一致方程式且我們利用收縮原理來證明其局部收斂性。此外我們探討了此演算法的收斂速度。接著進行了模擬計算並分析三筆真實數據,來說明此概似比統計量之卡方漸進性的適當性和此演算法的可行性。
    Current status censored failure time observation consists only of an examination time and knowledge of whether the failure time has occurred before the exam. Several semiparametric regression methods which examine the relationship between the failure time and covariates have been proposed extensively for current status data. In this thesis, we consider the likelihood ratio test for testing covariate effect under the proportional hazards model with current status data and propose an easily implemented algorithm for computing the statistics. The algorithm proposed is based on a set of self-consistency equations and its convergence is proved by contraction principle. Besides we discuss the rate of convergence of the algorithm. The adequacy of the Chi-squared approximation for likelihood ratio statistics and the availability of the algorithm are demonstrated in simulation studies and in the analyses of three real data.
    顯示於類別:[數學學系暨研究所] 學位論文

    文件中的檔案:

    檔案 大小格式瀏覽次數
    index.html0KbHTML112檢視/開啟

    在機構典藏中所有的資料項目都受到原著作權保護.

    TAIR相關文章

    DSpace Software Copyright © 2002-2004  MIT &  Hewlett-Packard  /   Enhanced by   NTU Library & TKU Library IR teams. Copyright ©   - 回饋