臺灣博碩士論文加值系統

許多生物醫學方面之研究，經常需要分析數個事件 (multiple endpoints) 的資料。而處理這種屬於多重路徑 (multi path) 的問題，常遭遇的難度之一是如何處理那些因設限而無法辨識其路徑的觀測值。
本論文首先從半競爭風險和長期倖存者兩種觀念來研究此問題並建構多重路徑的資料模式。進一步將以logistic regression探討解釋變數對於路徑選擇的影響，並分別在上述的兩種資料模式下提出合理的參數估計方法。

Many interesting biomedical applications involve analysis of multiple endpoints. Statistical inference based on multi-path is especially challenging due to the problem of non-identifiability.
In this article, we concern about two concepts of semi-competing risks and long term survivors, then build the multi-path models. We use logistic regression to discuss the inference of path choosing. Our approach provide reasonable parameter estimator under two kinds of data structure.

第一章 簡介 …………………………………………………………………………1
(1.1) 背景介紹 ……………………………………………………………………..1
(1.2) 動機 …………………………………………………………………………3
(1.3) 資料型態………………………………………………………………………4
第二章 文獻回顧 …………………………………………………………………7
(2.1) 無母數分析－根據長期倖存者資 …………………………………………7
(2.2) 以Mixture方式分析－根據長期倖存者資料 ……………………………9
(2.3) 以半競爭風險資料分析長期倖存者 ...…………………………………….10
第三章 邏輯斯迴歸模式下的統計推論 …………………………………………13
(3.1) 邏輯斯迴歸模式概述 ……………………………………………………..13
(3.2) 完整資料下之估計函數 …………………………………………………..13
(3.3) 長期倖存者資料之參數估計 ……………………………………………..14
(3.4) 半競爭風險資料之參數估計 ……………………………………………..15
(3.5) 合併估計方法 ……………………………………………………………..19
(3.6) 討論 “Redistribution to the right” 觀念的應用 ……………………….20
第四章 模擬實驗 …………………………………………………………………23
(4.1) 資料的生成 ………………………………………………………………..23
(4.2) 結果 ………………………………………………………………………..25
第五章 結論 ………………………………………………………………………28

References
Cox, D. R. & Oakes, D. (1984). Analysis of survival data. London, Chapman and Hall.
Kuk, Anthony Y. C. & Chen, C, H. (1992). A mixture model combining logistic regression with proportional hazards regressions. Biometricka 79, 531-541
Farewell, V. T. (1982). The use of mixture models for the analysis of survival data with long-term survivors. Biometrics 38, 1041-6.
Farewell, V. T. (1986). Mixture models in survivor analysis. Can. J. Statist. 14,257-262.
Fine, J. P., Jiang, H. and Chappell, R. (2001). On semi-competing risks data. Biometrika 88, 907-919.
Heckman, J. J. & Honor , B. E. (1989). The identifiability of the competing risk model. Biometrika 76, 325-330
Lin, D. Y., Robins, J. M. & Wei, L. J. (1996). Comparing two failure time distributions in the presence of dependent censoring. Biometrika 83,381-393.
Maller, R. A. and Zhou, S. (1992). Estimating the proportions in a censored sample. Biometrika 79, 731-739.
Maller, R. A. and Zhou, S. (1996). Survival analysis with long-term survivors.Chich-ester, U.K.: John Wiley and Sons.
Pepe, M. S. (1991). Multiple endpoint studies. J. Am. Statistic. Assoc. 86, 770-778.
Prentice, R. L. & Kalbfleisch, J. D., Peterson, A. V., Flournoy, N., Farewell, V. T.,Breslow, N. E. (1978). The analysis of failure times in the presence of competing
risks. Biometrics 34, 541-554.
Slud, E. V. & Rubinstein, L. V. (1983). Dependent competing risks and summary survival curves. Biometrika 70, 643-649.
Stephen W. Lagakos (1976). A stochastic model for censored-survival data in the presence of an auxiliary variable. Biometrics 32, 551-559.
Weijing Wang (2002). Nonparametric Estimation of the Sojourn Time Distribution for a Multi-Path Model. (under review by JRSSB)
Zheng, M. & Klein, J. P. (1995). Estimates of marginal survival for dependent competing risks based on an assumed copula. Biometrika 82, 127-138.