比較多個處理之群序檢定方法

淡江大學機構典藏 > 商管學院 > 統計學系暨研究所 > 學位論文 > Item 987654321/33858

jsp.display-item.identifier=請使用永久網址來引用或連結此文件: https://tkuir.lib.tku.edu.tw/dspace/handle/987654321/33858

题名:	比較多個處理之群序檢定方法
其它题名:	Group sequential methods for multi-armed trials
作者:	曾家誼;Tseng, Chia-yi
贡献者:	淡江大學統計學系碩士班陳怡如;Chen, Yi-ju
日期:	2005
上传时间:	2010-01-11 04:36:31 (UTC+8)
摘要:	針對臨床試驗的累積資料(accumulated data)，常見的期中分析群序方法為Pocock (1977)， O''Brien 與Fleming (1979)以及Lan 與 DeMets (1983)等三種方法。本文將探討Pocock方法， O''Brien-Fleming方法與三個顯著水準支配函數 $alpha_{1}^{}(t)=alpha{t}$ ， $alpha_{2}^{}(10,t)=alpha[(1-e^{-10t})/(1-e^{-10})]$ 及 $alpha_{3}^{}(-10,t)=alpha[(1-e^{10t})/(1-e^{10})]$ 所產生的臨界值之差異，並討論其所需的樣本數與固定樣本數之比較，同時利用Pocock提出各階段名目顯著水準 $alpha''$ 的概念，計算出不同階段下的群序卡方檢定和群序 $F$ 檢定之臨界值，此計算過程比Jennison與Turnbull(1991)所提出的方法較為簡易並且其臨界值結果非常近似。此外，本文著重討論 $J$ $(Jgeq3)$ 個處理之群序檢定過程，以實例說明比較三種處理之群序檢定，同時採用Bonferroni及LSD方法進行多重比較。 For accumulated data of clinical trials, three common group sequential methods were proposed by Pocock (1977), O''Brien and Fleming (1979), and Lan and DeMets (1983). The comparison of boundaries among Pocock''s method, O''Brien-Fleming''s method and three alpha spending functions: $alpha_{1}^{}(t)=alpha{t}$, $alpha_{2}^{}(10,t)=alpha[(1-e^{-10t})/(1-e^{-10})]$ and $alpha_{3}^{}(-10,t)=alpha[(1-e^{10t})/(1-e^{10})]$ is discussed. We adopt the concept of nominal significance level $alpha''$ presented by Pocock to calculate the boundaries of group sequential chi-squared test and group sequential $F$ test for various of overall significance level $alpha$ and testing stages $K$, which result in the similar critical values of chi-squared test computed by Jennison and Turnbull (1991). The required treatment sample size, maximun sample size and average sample size for each method are compared with the fixed sample size. Furthermore, the group sequential $F$ procedure for multi-armed trials and the corresponding multiple comparisons are illustrated by an example.
显示于类别:	[統計學系暨研究所] 學位論文

文件中的档案:

档案	大小	格式	浏览次数
	0Kb	Unknown	317	检视/开启

在機構典藏中所有的数据项都受到原著作权保护.

TAIR相关文章

数据加载中.....