A confidence interval won't adjust the points (point estimates) but will give those points with a lower sample size wide confidence intervals (often covering zero).
Using an (empirical) Bayesian multilevel model can both attach uncertainty intervals to the point estimates and appropriately "shrink" the estimates towards zero at the low-sample-size end.
The latter is more directly interpretable, at the cost of slightly more complex modelling (/assumptions).
Just so people know, there is a competing/complementary approach to causality in statistics, called the potential outcomes or (Neyman-)Rubin causal model, which as I understand it is currently more popular than Pearl's graphical/do-calculus approach.
I don't think machine learning vs Bayes vs sampling theory has much to do with the content of the article, which is more about causality than interpretations of probability.
> it's far more likely that coffee causes cancer if it can accurately predict it, even when you control for all other variables
I don't know about this: prediction is not equivalent to explanation in general. The "all the other variables" bit is also a bit of a kicker (what counts as "all"?) -- hence randomization, and, well, pretty much everything else the article discusses.
There are some distinct ideas that this article at times seems to conflate:
- Obscurity, speaking in fables, non-clarity, indirectness. Multiple layers to one's teaching. This possibly for the sake of pedagogy.
- Teachings for the public versus teachings for the initiates/elite/true disciples. Two contradictory or opposed layers to one's teaching.
The former and the latter are quite different, and I wonder whether the latter might be far less common than the former.
It seems clear that some thinkers, particularly in ancient Greece and Rome, had opposed esoteric and exoteric aspects to their work, and that we should acknowledge and try to discern this where it exists.
But I'd question whether esotericism is "of the greatest importance for our understanding of the whole course of Western philosophy". The author seems to think of it almost as a kind of skeleton key, as though maybe there is a significant stream of thought that people have radically misunderstood. The idea of a hidden thread of elite, secret knowledge has an alluring, conspiratorial feel to it that the author doesn't mention -- a vibe that is not so foreign to our modern sensibilities (Scientology, Kabbalah, New Age, ...).
Melzer writes that "with pedagogical esotericism, the writer actually embraces concealment and obscurity (of the right kind) as a positive good and as something essential to the primary purpose of his act of writing: philosophical education". How does this not describe art of all kinds -- e.g. fiction writing -- where the creator has a didactic purpose, but artfully weaves this into their work? ("Ars est celare artem.") Again, there is no distinction made between nonclarity and the demand for active, engaged, creative reading and thinking on the one hand, and on the other, radically opposed esoteric and exoteric meanings.