Dr.CardioMD said:

There is a difference between no evidence and evidence of no effect, and this subject is one where the two get swapped freely in both directions.

Careful with the causal language. Two things moving together in a period when five things changed is not a mechanism, and stating it as one makes the thread less useful to somebody reading it later.

The figures, for anyone assembling their own picture. Give anything pharmacological four weeks before you judge it, and give anything measured weekly a four-point rolling average before you call it a trend.

LabKate said:

Two things moving together in a period when five things changed is not a mechanism, and stating it as one makes the thread less useful to somebody…

Coming at LabKate’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.

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

How would you tell the difference between that and the alternative explanation?

Closing the loop on my own question.

For the archive: it took about six weeks rather than the two I expected, and the difference between those two numbers was the whole of my problem.