@tklebel.bsky.social
Senior Researcher @ Know Center. I'm interested in what AI does to science, how we can be more reproducible when conducting studies, and how we can make studies more robust and informative by using causal inference techniques.
Yes indeed, thanks a lot!
03.02.2026 16:00 — 👍 1 🔁 0 💬 0 📌 0"Honest, dedicated, skilled researchers may investigate a topic and come to opposite conclusions because of variation between how they conduct their analysis"
My sense is almost all experienced researchers are intuitively aware of this, but nevertheless we tend to ignore this inconvenient truth!
New blog post introducing Causion - a web app for causal inference teaching and learning: pedermisager.org/blog/causion....
28.01.2026 09:23 — 👍 134 🔁 61 💬 5 📌 6Just like democracies are being put to the test around the world (and succumbing sooner than we hoped), our ideals of research integrity and scientific rigor are being tested by ever-invasive AI tools. I am not hopeful science will survive this unscathed. We'll need to rethink a lot of what we do.
28.01.2026 16:48 — 👍 69 🔁 19 💬 2 📌 4Fair point. It was quite difficult to come up with a single reasonable DAG that illustrated all the aspects we wanted to highlight.
But also: our point is exactly that DAGs can help expose our assumptions so we can interrogate them more thoroughly.
As a sidenote: the article was also a great (and in many instances tedious) exercise in writing a fully reproducible manuscript. I think it was worth it, but definitely led to some headache and frustration (especially since we wanted the result to look pretty).
27.01.2026 10:36 — 👍 1 🔁 1 💬 0 📌 0Hoping that our article will make a change and prompt colleauges in science studies to think more thoroughly about their analyses and the claims they make based on their research designs.
27.01.2026 10:36 — 👍 1 🔁 1 💬 1 📌 0Just as @devezer.bsky.social posted today, there is still much to do to spread the world beyond the online bubble.
27.01.2026 10:36 — 👍 1 🔁 1 💬 1 📌 0I believe many people are unaware of common pitfalls, such as the table 2 fallacy (interpreting individual regression coefficients causally) and/or might have never heard about "collider bias", which @vtraag.bsky.social illustrates here.
27.01.2026 10:36 — 👍 2 🔁 1 💬 1 📌 0Happy to share our recent article on causal inference in science studies. It aims to introduce causal thinking to the science of science community with an example from Open Science.
27.01.2026 10:36 — 👍 8 🔁 2 💬 1 📌 0
