Psea, The p-value that FDA will use I think wil

Psea,

The p-value that FDA will use I think will remain set and is usually 0.05.
Now, if the survival rate is small (once the criteria for serious condition has been defined) chances are that there will be, unfortunately, a number of events (deaths).

I think FDA designed the two week timeframe conscious that there will be enough statistics for analysis, they already must know what approximate figures are.

Now, in order to use a binomial distribution some conditions must be met:

The number of observations (patients) is fixed.
Each observation is independent.
Each observation represents one of two outcomes ("success" or "failure".
The probability of "success" p is the same for each outcome.

In our case, if some patients are switched over to another arm, or Lero’s arm, two conditions will be violated: the number of observations will not be fixed and the probability of success will not be the same for each outcome as patients that need to be retired will not count in the “failure” outcome, biasing the results against Leronlimab arm.

If this is this case, patients will be effectively "re-assigned" in sequential order (depending on patients well being) FDA could stop the trial when a predefined endpoint is reached. This is called curtailed sampling.

Under curtailed sampling, the range of the sample size can be smaller. For example, they observe that some patients in the placebo arm have to be switched to other treatment, and this happens with much less patients in the Lero arm as they are doing well (surviving). They can stop the trial short and determine that Leronlimab achieved statistical significance.

This, of course need continuous monitoring, the formula for curtailed sampling is more complicated and, of course, we don’t know what the numbers would look like (to achieve significance). However in this case, being a "double blind" trial nobody knows who is treated with what.

I will assume then that, either a patient removed is treated as a failure, or, simply, patients dropping out will be taken into account in the calculation as secondary endpoints.

I am not privy to what these are.