劉仁沛臺灣大學：農藝學研究所童聖哲Tung, Sheng-CheSheng-CheTung2007-11-282018-07-112007-11-282018-07-112004http://ntur.lib.ntu.edu.tw//handle/246246/59147根據美國食品與藥物管理局(FDA)的準則，安定性試驗的目的是根據至少檢定三個批次的藥品來建立該藥品的有效期限，並可應用於所有未來於相同環境下製造出來的藥品。然而在現實長期的檢定架構下，要檢定所有不同時間、強度、儲存條件及包裝方式下的每個批次可能相當耗費金錢和時間，因此縮減性設計便可被視為既能減少檢定次數又能獲得所需訊息的一種有效率的方法。本篇論文利用統計的觀點討論關於現行準則中安定性試驗的各種設計，並利用幾種常用的準則來比較這幾種設計。 另外，當考慮不同因子可否合併估計一個共同有效期間時，Tsong等人提出利用平均值法進行檢定，我們根據Tsong的方法提出配對信賴區間進行檢定。最後利用模擬研究發現不論以型一誤差（size）或是檢定力（power）的觀點，我們提出的方法似乎會是較好的選擇。According to U.S. Food and Drug Administration (FDA) guidelines, the purpose of a stability study is to establish, based on testing a minimum of three batches of the drug substance or product, a retest period or shelf life and label storage instructions applicable to all future batches manufactured and packaged under similar circumstances. However, to test every batch under all possible combinations of time, strength, storage conditions, and packaging methods on a long-term testing schedule can be expensive and time consuming. As an alternative, a reduced design may be considered as an efficient method for reducing the number of testings needed to obtain the necessary information. In this thesis, we discuss the statistical aspects of stability study designs in relation to the recent guidelines. In addition, several commonly used criteria for design comparison are presented. Based on Tsong’s mean value method, we propose a procedure to test the hypothesis for pooling factors. Finally, a simulation study was conducted to empirically compare the performance of the two methods in terms of size and power in estimating the shelf life of the drug product. Simulation results show that our simultaneous pairwise C.I.s method is superior to Tsong’s method.Chapter 1 Introduction 1 1.1 Stability Study 1 1.2 Determination of Drug Shelf Life 4 Chapter 2 Stability Study Designs 6 2.1 Types of Stability Study Designs 7 2.1.1 Full Design vs. Reduced Design 7 2.1.2 Bracketing Design vs. Matrixing Design 9 2.2 Criteria for Design Selection 14 Chapter 3 Statistical Approaches to Stability Data Analysis 19 3.1 Data Analysis for a Single Batch 19 3.2 Testing for Poolability of Batches 23 3.2.1 Equivalence Limit Method 25 3.2.2 Proposed Method 27 3.3 Examples 29 Chapter 4 Simulation Study 36 4.1 Simulation Procedure 36 4.2 Simulation Results 38 4.2.1 Empirical Size for Combinations of factors 38 4.2.2 Empirical Power for Combinations of factors 40 Chapter 5 Discussion and Concluding Remarks 44 References 45 Appendix 48691256 bytesapplication/pdfen-US縮減性設計估計藥品有效期間合併批次安定性試驗Stability studyreduced designshelf life estimationpooling batchesthesishttp://ntur.lib.ntu.edu.tw/bitstream/246246/59147/1/ntu-93-R91621211-1.pdf