That is just fabulous! I never thought about it that way, but it is worth doing so!

BTW, was showing your slide on the non-causal psych research yesterday in class! We discussed the multilingualism paper. I wanted to thank you for all the very interesting things you are doing!

Me neither until I realised I was one of them 🤣 (Part of my stance is anti-realist/idealist and anti-positivist so ultimately I believe there is no objective reality but then we straddle onto spiritualism which is another part of my stance). I guess it’s just more complicated, like most things! :)

I disagree with “It’s not like Bayesians don’t believe in true parameters that take on certain values; the true parameters are just unknown”. Some do not believe in true parameters (depends on your philosophical stance). :)

We could also discontinue the traditional way of publishing (there is little evidence that peer review improves the quality of the research). That would also redirect money from for-profit publishing companies to other things.

This slide unfortunately generalizes well 🥲

And if this article is right, this is the perfect example of the underspecification of the theory. If people double-downed on the cult, it's because they reduced cognitive dissonance. Now it may turn out that people disbanded the cult. Well, it's because they reduced cognitive dissonance 😃

One example is that he never refers to 3I/ATLAS as an “alien spaceship” but as an “interstellar object” when strictly referring to it (I’m talking about the concept of referring expressions, not about when speculations about the object are made). People should learn a bit of linguistics perhaps.

I agree with Timo! Of course applicability varies by discipline, but in linguistics it is often very difficult if not impossible to come up with a SMES (Smallest Meaningful Effect Size, as I call it in Bayesian inference, although the concept is similar to SESOI).

I know it is difficult to do this here, but could you expand on what you take "science" to be? (I ask because my positionality makes it so I don't much care for "science", but I want to make sure we are talking about the same thing). :) (Love your work by the way! And the students like it too!)

But why doing equivalence testing when one can learn from a full posterior probability distribution? (Maybe I am biased because I don't think dichotomous decision have a place in knowledge-oriented research)

It’s not been an issue so far. Students who engage, engage, those who don’t, don’t (these are very very few tho. The course ha about 90/100 students). I see most of these back again during dissertation writing and they are on top of things.

That said, assessment is a university policy that cannot be changed so this is what I do: uoelel.github.io/qml/assessme...

(Funny enough, while courses have to be assessed, there isn't anything in the UK law that says that they have to be marked and what the marks should be)

I don't think we can ever "effectively assess" knowledge, so I gave up.

"Until a system of absolute mental units has been invented, it is futile to try to make grades represent absolute accomplishment." doi.org/10.1126/scie...