Designed extension of studies based on conditional power.

摘要: We propose a flexible method of extending study based on conditional power. The possibility for extension when the p value at planned end is small but not statistically significant built in to design study. significance treatment difference used determine number additional observations needed and critical necessary use after accruing those observations. It may therefore be thought as two-stage procedure. Even though observed stage 1 make decisions, Type I error rate protected.