臨床試驗評估等效性可藉由三臂試驗來執行。實際應用上，三臂等效試驗含三個假設檢定，其中二個檢定考驗實驗用藥及參考用藥對安慰劑的優越性以及一個檢定考驗實驗用藥及參考用藥的等效性。文獻上針對研究目的為存活時間的試驗計算所需樣本數的方法相當有限，因此本研究計畫的目的在於彌補文獻上的不足針對蒐集設限存活時間的三臂臨床試驗開發新的樣本數計算方法。我們首先考量存活時間來自於廣義的參數分布。此外,把組別視為獨立變數,則半母數風險回歸模型可用於樣本數之計算。我們主要考量非比例半母數風險模型包含了加速失敗時間模型及擴充風險模型。本計畫所提之方法將應用在旅行者腹瀉臨床試驗並用模擬研究來確認計算方法的正確有效性。 ;The assessment of equivalence in a clinical trial may be conducted through a three-arm trial (test drug, reference drug, and placebo). The three-arm equivalence trial consists of three hypothesis tests in practice, where two hypothesis tests are demonstrating the superiority of test drug and reference drug against placebo, and the other one is demonstrating the equivalence of test drug and reference drug. In the literature, so far, the sample size determination for three-arm design with survival endpoints is limited. Therefore, to complement the literature, the purpose of this study is to develop a statistical method to calculate the sample size for three-arm equivalence trials with censored survival outcome as the primary endpoint. General classes of parametric distributions will be considered to calculate the sample size. Moreover, treating the three groups as covariates, the semi-parametric hazards regression model can be employed to the three-arm testing procedure. The non-proportionality hazards regression models including the AFT and extended hazards models will be applied to the sample size determination. We illustrate the use of the method by considering a randomized, active- and placebo-controlled trial in subjects with travelers’ diarrhea. The validity of the proposed method will be investigated by simulation studies.
