Adding the numbers, since they settle part of this. If you are comparing against somebody else’s result, check that you are comparing the same measurement taken the same way. Most of the apparent contradictions in these threads dissolve at that step.

One thing that is still open after sean_dublin’s answer:

How long did you give it before you decided it was working?

BiostatsBrad said:

If you are comparing against somebody else’s result, check that you are comparing the same measurement taken the same way.

I do not accept the framing. The question has been narrowed to the version that has a tidy answer, and the part that was dropped is the part the OP actually asked about.

BiostatsBrad said:

If you are comparing against somebody else’s result, check that you are comparing the same measurement taken the same way.

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.

BiostatsBrad said:

If you are comparing against somebody else’s result, check that you are comparing the same measurement taken the same way.

Genuinely useful, thank you. I had the facts and not the framework. Printing the relevant bit and taking it with me.