三臂試驗設計包含實驗組、對照組以及安慰劑組，又可以稱為黃金標準設計，這種試驗設計除了可以比較實驗組與對照組外，分別對於安慰劑組的藥效和療效也可以從試驗中得知。本篇研究目的為在三臂非劣性試驗中，以存活時間為主要目標，採用參數比例風險模型 (proportional hazards model,PH)，包含weibull、Loglogistic、Rayleigh、Gompertz分配，用來探討各治療組別樣本最佳分配比例以及最佳樣本數，並確認相對的檢定力是否達到預設值。本研究也透過結腸癌資料集去說明與闡述本篇論文所適用的方法。;The three-arm trial design includes an experimental group, a control group, and a placebo group, also known as a gold standard design. This type of trial design allows for comparison not only between the experimental and control groups but also provides information about the efficacy and therapeutic effects of the placebo group. The purpose of this study is to utilize the three-arm non-inferiority trial, with the primary objective being survival time. The study adopts the proportional hazards model (PH) with various distributions such as Weibull, Loglogistic, Rayleigh, and Gompertz, to explore the optimal allocation proportions and sample sizes for each treatment group. Additionally, it aims to verify whether the corresponding test power meets the predetermined value. This study also utilizes a colon cancer dataset to demonstrate and elaborate on the methods applicable to this research paper.
