Thanks, ohm. thats all very logical.
But for the logic to hold true, does it not require that CD12 report at least 50% mortality reduction?
I am gong from memory, but I believe more than one statistically-saavy poster has offered a statistical analysis here which casts doubt on the "power" numbers even in the event of a 50% mortality reduction.
I lack the stats math skills to check those posters. Perhaps I have misunderstood those posters.
Many posters have offered statistical analysis here as to the mortality reduction which would be achieved for p<0.05.
At the interim, the mortality reduction for p<0.05 was around 50%.
At 390, the mortality reduction for p<0.05 was around 33%.
But since I am clueless on these statistics, I now believe that efficacy (in other words mortality reduction) is a variable component in the "power" function equation, and that hitting a normal "power" number will require a mortality reduction greater than 50% which oh-by-the-way provides a p-value that is much less than 0.05.
So my conclusion is that if your logic and analysis is correct, then CD12 will report greater than 50% mortality reduction vs. placebo.
Why am I so obsessed with this?
I simply cannot believe that any sane minded human being would, upon observing 50% mortality reduction at the interim, allow the trial to continue. I just can't believe that.
But as you say, perhaps the DSMC did attempt to bring the trial in early by switching to 42 day mortality.
And then the DSMC's effort to bring it in early was mooted by the dramatic accleration in enrollment.
Part of the reason I cannot believe anyone would let the trial run upon observing 50% mortality reduction is that whoever let it run would have to answer for the delay in approval.
Perhaps those who did let it run considered their effort to obtain a 75% interim as the proper response.
Some of those who did let it run may be FDA employees. Perhaps those FDA employees see EIND and OLE expanded access options as proper responses to the situation.
In any event, it seems to me that if your analysis is correct, CD12 will report at least 50% mortality reduction and perhaps significantly greater.
But what do I know? I fell more confused than anything else
But for the logic to hold true, does it not require that CD12 report at least 50% mortality reduction?
I am gong from memory, but I believe more than one statistically-saavy poster has offered a statistical analysis here which casts doubt on the "power" numbers even in the event of a 50% mortality reduction.
I lack the stats math skills to check those posters. Perhaps I have misunderstood those posters.
Many posters have offered statistical analysis here as to the mortality reduction which would be achieved for p<0.05.
At the interim, the mortality reduction for p<0.05 was around 50%.
At 390, the mortality reduction for p<0.05 was around 33%.
But since I am clueless on these statistics, I now believe that efficacy (in other words mortality reduction) is a variable component in the "power" function equation, and that hitting a normal "power" number will require a mortality reduction greater than 50% which oh-by-the-way provides a p-value that is much less than 0.05.
So my conclusion is that if your logic and analysis is correct, then CD12 will report greater than 50% mortality reduction vs. placebo.
Why am I so obsessed with this?
I simply cannot believe that any sane minded human being would, upon observing 50% mortality reduction at the interim, allow the trial to continue. I just can't believe that.
But as you say, perhaps the DSMC did attempt to bring the trial in early by switching to 42 day mortality.
And then the DSMC's effort to bring it in early was mooted by the dramatic accleration in enrollment.
Part of the reason I cannot believe anyone would let the trial run upon observing 50% mortality reduction is that whoever let it run would have to answer for the delay in approval.
Perhaps those who did let it run considered their effort to obtain a 75% interim as the proper response.
Some of those who did let it run may be FDA employees. Perhaps those FDA employees see EIND and OLE expanded access options as proper responses to the situation.
In any event, it seems to me that if your analysis is correct, CD12 will report at least 50% mortality reduction and perhaps significantly greater.
But what do I know? I fell more confused than anything else
2
