hank_denver said:

One habit that pays for itself: post the method alongside the number.

Pushing back on hank_denver here. I would resist the confidence. Half of what this board was certain about two years ago has since been quietly dropped, and nobody went back to correct the threads.

hank_denver said:

One habit that pays for itself: post the method alongside the number.

True, with the qualification that this is a self-selected group. The people for whom it did not work post less, and that shapes everything we think we know.

Found this through search years later and it is still the best discussion of the question, so adding one thing. The boring version of this is the one that works, and the boring version is: measure a baseline, change one variable, wait, measure again under the same conditions. Nobody wants that answer and it is still the answer.

From the other side of the consultation, briefly. The honest answer is that the effect is real, the magnitude is contested, and the individual variation is larger than either. Those three things can all be true at once, and most arguments here are two people holding different parts of that.

jim_asheville said:

The honest answer is that the effect is real, the magnitude is contested, and the individual variation is larger than either.

Same experience, arrived at from the opposite direction.