In clinical drug development a typical phase three power calculation for a Go/No-Go decision is performed by replacing unknown population-level quantities in the power function with what is observed from a literature review or what is observed in phase two. Many authors and practitioners view this as an assumed value of power and offer the Bayesian quantity probability of success or assurance as an alternative. The claim is by averaging over a prior or posterior distribution, probability of success transcends power by capturing the uncertainty around the unknown true treatment effect and any other population-level parameters. We use confidence distributions to frame both the probability of success calculation and the typical power calculation as merely producing two different point estimates of power. We demonstrate that Go/No-Go decisions based on either point estimate of power do not adequately quantify and control the risk involved, and instead we argue for Go/No-Go decisions that utilize inference on power for better risk management and decision making. This inference on power can be derived and displayed using confidence distributions.
翻译:在临床药物开发中,对Go/No-Go决定进行典型的三阶段功率计算,方法是用文献审查或第二阶段观测到的文献来取代动力功能中未知的人口数量。许多作者和从业者认为这是一种假定的力量价值,提供了巴伊西亚数量的成功概率或保证作为替代办法。这种主张是通过先前或后期分配的平均值,成功概率通过捕捉未知的真实治疗效应和其他人口参数的不确定性而超越权力。我们利用信任分布来设定成功率的概率和典型功率计算,仅仅作为产生两种不同的功率估计值。我们证明,根据对权力的两点估计,Go/No-Go决定不能充分量化和控制所涉风险,而我们则主张Go/No-Go决定利用权力的推论来更好地风险管理和决策。这种对权力的推论可以通过信任分布来得出和显示。