Study design confirmatory trials

Therapeutic exploratory (Phase lb/II) Explore use for the targeted indication Estimate dosage for subsequent studies Provide basis for confirmatory study design, endpoints, methodologies Earliest trials of relatively short duration in well-defined narrow patient populations, using surrogate or pharmacological endpoints or clinical measures Dose-response exploration studies... 

The rationale and design of confirmatory trials nearly always rests on earlier clinical work carried out in a series of exploratory studies. Like all clinical trials, these exploratory studies should have clear and precise objectives. However, in contrast to confirmatory trials, their objectives may not always lead to simple tests of pre-defined hypotheses. ... 

What information from early phase trials may be used to inform the study designs of therapeutic exploratory and therapeutic confirmatory trials ... 

In this chapter we highlight additional statistical considerations relevant to therapeutic confirmatory trials, and other study designs that also provide important information upon which to base decision-making. These additional insights and information build upon the material presented so far. As this chapter is largely conceptual rather than computational, we have included a number of references to guide your further reading. 

Both a and p are design parameters, and are chosen at the discretion of those designing the trials. In confirmatory trials, a is 0.05 and p is typically 0.10 or 0.20 (meaning that the study has 90% or 80% power, respectively). The choices of a and A are not quite as straightforward, because the range of possible values is... 

The short answer is that it depends on the power (and therefore the sample size) of the study. To illustrate this, assume that the value of the design parameter a is dictated by regulatory concerns, which is reasonable especially in confirmatory trials. Further, before a new study is completed there is still some doubt as to whether the new treatment is efficacious, such that the value of x is conjectured to be 0.5. Resulting values of the error rates, a and p, are presented in Table 12.1 as a function of the power (or, equivalently, P) of the study. 

---