Destined to fail, page-26

For disclosure right up front, I have never been involved in this sort of medical trial or anything involving statistical significance - but I do have a degree in maths, for what it's worth.

I have a problem with your assertion A. And this goes back to what PFS means for the trial group. And sadly I don't know the answer in this specific medical context. But here's my thinking - if you give a treatment to a large number of people and it doesn't help some, but does help others (even to the extent of curing them) I'm not sure you can claim that the treatment was the cause of any improvement to any of them. It could have been some other random event like the weather.

Conversely if you can say that a specific sub group, (which you can clearly identify), ALL had PFS for x months more than the control group, then you can attribute that to the specific treatment. I hope I've explained that correctly. I guess an analogy would be giving a headache tablet to a group of people, some with broken legs, some with a headache. Half the people might be cured of the headache, but the other half still have broken legs. You can't just average the results out and say it partially works. But it might completely cure those with the headache.

This is why "destined to fail" is exactly the right subject of this thread (unless they were hoping for a miracle cure). But I am most interested to see if they can show statistical and clinical significance to a clearly defined sub-group of patients in the trial, and of course how big that sub-group is.