摘要
隨著科技、經濟的快速發展，使得製藥產業已邁向全球化。然而有鑑於藥物的特性可能因國與國之間存在著某些內因性與外因性的差異而有不同的療效，而影響著藥品的療效與安全性，因此如何檢定不同族群間的人種差異便是當今一項重要的課題。本文利用統計的理論觀點，以更科學嚴謹的角度來檢定人種差異，使國外的臨床實驗資料可以推到新地區使用，以減少不必要的臨床實驗。在過去文獻中，已有一些檢定人種差異的方法已被提出，而本文所提利用兩區域之非中心參數來判定人種差異存在與否的方法，是假設在兩區域樣本數平衡之情況下，虛無假設在指定兩區域之非中心參數等於某一定值時做檢定，分別在兩區域樣本數相等且同區域變異數相等下作討論，建構一模擬研究，比較新方法在不同的情況下的檢定力的優劣，以了解本文之檢定方法之可行性。
並列摘要
With the fast development of the science and technology, the Pharmacy industry already make globalize. However, the efficacy and safety variations of the new drug among different geographic regions may exist,due to ethnicity intrinsically or extrinsically. So that, constructing a method to evaluate the ethnic difference between countries has been an important issue recently. The purpose of this paper is to study some statistical methodologies to assess ethnicity sensitivity, in order to reduce the unnecessary clinical experiment and allow foreign clinical experiment can be extrapolated to the new region. This paper adopts the concepts of noncentral t parameters to testthe difference of clinical results between two regions. A simulation study was conducted to evaluate and compare the power in different cases.