JenPlateau 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. I had assumed I was the exception until I read this.

stefan_berlin said:

Say what you would expect to see if you were wrong, before you look.

I read this differently. The confidence in this thread is running ahead of the evidence, and I would rather the uncertainty were stated than smoothed over because it is unsatisfying.

stefan_berlin said:

Say what you would expect to see if you were wrong, before you look.

That is right for the common case. Whether it is right for the case being asked about depends on a detail that has not been given.

stefan_berlin said:

Say what you would expect to see if you were wrong, before you look.

Saving this. It is the first explanation that did not require me to already understand it. Printing the relevant bit and taking it with me.

Moderator note: the sourcing question belongs in the vendor section and has been split out.