HPLC_Greg said:

It helps to say which part of this you are uncertain about.

Fair, and it stops being fair at the extremes. The middle of the range is well understood; the ends are where the honest answer is that nobody knows.

Old thread, but it comes up first when you search for this, so it is worth updating. Keep the original post as written when you update it, and add the correction underneath. An edited-away mistake is invisible to the next person who makes it.

Ask again with the specifics and you will get a better answer than this one.

Clinical perspective, offered as context rather than as advice. Whatever the answer turns out to be, the method for getting there is the same: state the assumption, do the arithmetic in public, and invite the correction. That is slower than asserting, and it is the only version that survives being wrong.

If somebody has the primary source to hand I would rather cite it than paraphrase it.

pete_nash said:

Whatever the answer turns out to be, the method for getting there is the same: state the assumption, do the arithmetic in public, and invite the…

This is my experience too, for whatever a second data point is worth.

pete_nash said:

Whatever the answer turns out to be, the method for getting there is the same: state the assumption, do the arithmetic in public, and invite the…

Coming at pete_nash’s question from a different direction. Most of what circulates confidently in this community traces back to one summary of one study, and the qualifier was dropped somewhere in the third retelling.