You have to be very, very when discussing the placebo effect to distinguish between reporting differences and actual differences. That gets very complicated when you only have self-reporting of a subjective state to evaluate things on.

The classic study was on asthma treatments. Patients would subjectively report feeling better when on the placebo treatment, but the objective measurements of lung function showed no difference.

If people report being in less pain or less depressed when on a placebo treatment but attempt & complete suicide at the same rate... well, fuck.

That was not meant dismissive, the placebo effect is of course a well established and very real effect. But there is nothing more than the placebo effect in homeopathy.

Note that most of what we call placebo effect is actually return to the mean. True placebo effect exists but its much more limited than what people usually think.

Naively I would expect regression toward the mean to weaken the placebo effect - using a placebo seems a better idea in light cases and even in a controlled study you would probably not be allowed to only use placebos in severe cases so that it seems more likely that the situation worsens which would reduce the observed strength of the placebo effect in the other direction.

But placebo only work in the situations considered as light cases, where regression to the mean is still feasible. Once you consider cancer, severe infections or other stuff like that, there is no placebo effect anymore. That's why I said most of the placebo effect is regression to the mean, and once you study diseases where regression to the mean never occur, then the placebo effect is in-existent.