Application of randomization test in the sample size adjustment for internal pilot study
Su Wang · Di-Si Junyi Daxue xuebao · 2009
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.