随机化检验在内部预试验自适应设计样本量调整中的应用

Application of randomization test in the sample size adjustment for internal pilot study

目的:探讨随机化检验(Randomization test)在内部预试验IPS(Internal Pilot Study)自适应设计样本量调整中对I型错误和检验效能的影响.方法:利用蒙特-卡罗(MonteCarlo)法模拟样本量较小时的IPS样本量调整,分别采用随机化检验和t检验分析最后数据并比较二者对I型错误、检验效能值的影响.结果:重计算的第二阶段样本量波动性较大,t检验不能很好地抑制I型错误,随机化检验能较好的抑制I型错误,检验效能略有降低.结论:在临床试验样本量较小的情况下,内部预试验盲态下样本量调整后随机化检验能保护I型错误不增大,同时保证检验效能亦满足要求.

AIM：To probe into the effect of randomization test on type I error and power when it is used to ananlyze the data from IPS（Internal Pilot Study）with samplesize adjustment.METHODS：Monte Carlo was used to simulate IPS samplesize adjustment on condition that IPS samplesize is small.Randomization test and t test were used simultaneously to analyze the final data in order to compare the different effect of two methods on type I error and power.RESULTS：While the recalcultion sample size for the second phase is volatilely fluctuant,t test can not prevent type I error from inflating.However,randomization test can prevent type Ⅰerror from inflating better with little lower of power.CONCLUSION：The randomization test for the final data can not only prevent type Ⅰerror from inflating,but also maintain the desired power if we re-estimate the sample size under blinded IPS when it has small sample size.