This paper outlines the purpose and requirement for sample size reestimation, reviews some of the proposed methods, and discusses practical aspects of implementing the procedures. Special attention is paid to two issues: 1) keeping the interim relative treatment effect unrevealed, and 2) maintaining the overall Type I error rate.
PocockSJ. Group sequential methods in the design and analysis of clinical trials. Biometrika. 1977;64: 191–199.
2.
O'BrienPCFlemingTR. A multiple testing procedure for clinical trials. Biometrics. 1979;35: 549–556.
3.
LanKKGDeMetsDL. Design and analysis of group sequential tests based on the type I error rate function. Biometrika. 1983;74: 149–154.
4.
LanKKGSimonRHalperinM. Stochastically curtailed tests in long-term clinical trials. Com Stat (A). 1982;1(3):207–219.
5.
SpiegelhalterDJ. Probabilistic prediction in patient management and clinical trials. Stat Med.1986;5: 421–433.
6.
The PMA Biostatistics and Medical Ad Hoc Committee on Interim Analysis.Interim analysis in the pharmaceutical industry. Controlled Clinical Trials. 1993; In press.
7.
Clinical Trial Monitoring and Interim Analysis in the Pharmaceutical Industry—A PMA/FDA Workshop, Volume one, February 24–25, 1992. (Unpublished PMA document.).
8.
SteinC. A two-sample test for a linear hypothesis whose power is independent of the variance. Ann Math Stat. 1945;16: 243–258.
9.
WittesJBrittainE. The role of internal pilot studies in increasing the efficiency of clinical trials. Stat Med.1990;9: 65–72.
10.
ShihWJ. Sample size reestimation in clinical trials. Chapter 18. In PeaceKarl ed. Biopharmaceutical Sequential Statistical Applications. New York: Marcel Dekker; 1992:285–301.
11.
GouldALShihWJ. Sample size reestimation without unblinding for normally distributed outcomes with unknown variance. Com Stat (A). 1992;21(10):2833–2853.
12.
EverittBSHandDJ. Finite Mixture Distributions. London: Chapman and Hall; 1980.
13.
BehboodianJ. On the modes of a mixture of two normal distributions. Technometrics. 1970;12: 131–139.
