Power analysis helps design a trial at the beginning when writing the trial design. (Note this Power is defined as statistical Power and has nothing to do with the CEO Linda Powers)!
Essentially Powering the trial for a p=.02 Simply means that the trial N (312) is increased to achieve a p =.02 if there is a 6 month improvement in PFS for the treated patients. Hence the company is correct this N (312) provides some additional cushion in the event the reality is that the treated group only increase PFS by say 4 months. Even then, with the N of 312 and the possibility of increasing the N as per the study rules increases the chance that this trial will return a statistically significant result of at least a p<=.05. This AF guy is sneaky because he is correct that the Power is reduced when the p value is reduced from .05 to .02 but this is countered by the increase in the N (312) of the trail.
From Wikkibooks below:
Power analysis can be used to calculate the minimum sample size required so that one can be reasonably likely to detect an effect of a given size. Power analysis can also be used to calculate the minimum effect size that is likely to be detected in a study using a given sample size.
Statistical power may depend on a number of factors. Some of these factors may be particular to a specific testing situation, but at a minimum, power nearly always depends on the following three factors:
• the statistical significance criterion used in the test; Lower gives lower power
• the magnitude of the effect of interest in the population; Higher gives higher power
• the sample size used to detect the effect; Higher gives higher power
It is also important to consider the statistical power of a hypothesis test when interpreting its results. A test's power is the probability of correctly rejecting the null hypothesis when it is false; a test's power is influenced by the choice of significance level for the test, the size of the effect being measured, and the amount of data available
