在研發新藥的過程中，第二期臨床試驗的主要目的是要瞭解藥品的有效性與安全性，以做為是否進一步進行第三期臨床試驗的依據。多位學者已針對單變量二元療效指標(univariate binary endpoint)發展比較二組療效的臨床試驗設計，例如學者Barnard (1947)及學者Hollander與Wolfe (1999)的臨床試驗設計。由於藥品常對人體產生難以預知的副作用，對於受試者充滿了無法預知的風險，基於道德上的考量，臨床試驗執行者應避免提供無療效的藥給太多的受試者，因此，近年來，二階段設計被廣泛應用在新藥研發的第二期臨床試驗中，如學者Simon (1989)提出單組療效比較的二階段臨床試驗設計，此外，學者Jennison與Turnbull (2000)、學者Kepner (2009)則提出比較二組療效的二階段臨床試驗設計。

然而，這些設計的總試驗病患人數皆在試驗前即決定，因此，學者Herrmann與Szatrowski (1985)將學者Phatak與Bhatt (1967)所發展的縮減抽樣程序(curtailed sampling procedure)應用於單一階段(single-stage)單組二元療效指標的臨床試驗中，以期能夠減少試驗所需的受試者個數，進而縮短臨床試驗所需的時間。學者Chi與Chen (2008)更進一步對單組二元療效指標，提供縮減二階段臨床試驗設計，此試驗方式能在未完成預定招募受試者前，便能做成決策，有效減少受試者數目。所以，本論文將針對比較二組二元療效指標，提供縮減一階段和二階段臨床試驗設計，以期更早獲得試驗結果，加快進入第三期臨床試驗。

Recently, two-stage designs are widely applied in Phase II clinical trials to avoid providing inefficient drugs to many patients. For example, Simon’s (1989) two-stage design is for comparing one treatment response rate with a prespecified value, whereas Kepner’s (2009) two-stage design is for comparing two treatment response rates. However, for a promising new drug, these designs may still require a long observational period. Therefore, this thesis proposes curtailed single-stage and curtailed two-stage designs for comparing two binomial responses to shorten the drug development process as soon as one treatment either shows lack of efficacy or is very effective.

1. Barnard, G. A. (1947). Significance Tests for 2 × 2 Tables, Biometrika 34: 123-138.
2. Buzaianu, E. M. and Chen, P. (2009). A Hybrid Selection and Testing Procedure With Curtailment for Comparative Clinical Trials, Sequential Analysis, 28: 2-20.
3. Chi, Y. and Chen, C. M. (2008). Curtailed Two-stage Designs in Phase II Clinical Trials, Statistics in Medicine, 27: 6175-6189.
4. Herrmann, N. and Szatrowski, T. H. (1985). Curtailed Binomial Sampling Procedures for Clinical Trials with Paired Data”, Controlled Clinical Trials, 6: 25-37.
5. Hollander, M. and Wolfe, D. A. (1999). Nonparametric Statistical Methods(2nd ed.), John Wiley & Sons, Inc.
6. Jennison, C. and Turnbull, B. W. (2000). Group sequential methods with applications to clinical trials, Chapman & Hall/CRC.
7. Kepner, J. L. (2009). On Group Sequential Designs Comparing Two Binomial Proportions, Journal of Biopharmaceutical Statistics, 20: 145-159.
8. Phatak, A. G. and Bhatt, N. M. (1967). Estimation of the Fraction Defective in Curtailed Sampling Plans by Attributes, Technometrics, 9: 219-228.
9. Simon, R. (1989). Optimal Two-stage Designs for Phase II Clinical Trials, Controlled Clinical Trials, 10: 1-10